Targeted therapy aims to block tumor-driving signaling pathways and is generally based on analysis of one primary tumor (PT) biopsy. Tumor heterogeneity within PT and between PT and metastatic breast lesions may, however, impact the effect of a chosen therapy. Whereas studies are available that investigate genetic heterogeneity, we present results on phenotypic heterogeneity by analyzing the variation in the functional activity of signal transduction pathways, using an earlier developed platform to measure such activity from mRNA measurements of pathways’ direct target genes. Statistical analysis comparing macro-scale variation in pathway activity on up to five spatially distributed PT tissue blocks (n = 35), to micro-scale variation in activity on four adjacent samples of a single PT tissue block (n = 17), showed that macro-scale variation was not larger than micro-scale variation, except possibly for the PI3K pathway. Simulations using a “checkerboard clone-size” model showed that multiple small clones could explain the higher micro-scale variation in activity found for the TGFβ and Hedgehog pathways, and that intermediate/large clones could explain the possibly higher macro-scale variation of the PI3K pathway. While within PT, pathway activities presented a highly positive correlation, correlations weakened between PT and lymph node metastases (n = 9), becoming even worse for PT and distant metastases (n = 9), including a negative correlation for the ER pathway. While analysis of multiple sub-samples of a single biopsy may be sufficient to predict PT response to targeted therapies, metastatic breast cancer treatment prediction requires analysis of metastatic biopsies. Our findings on phenotypic intra-tumor heterogeneity are compatible with emerging ideas on a Big Bang type of cancer evolution in which macro-scale heterogeneity appears not dominant.