Performing live-cell microscopy and high-dimensional gene expression measurements on the same cells is crucial for unraveling the molecular mechanisms underlying complex temporal phenotypes, yet this remains challenging using traditional approaches. To address these limitations, we developed Video Imaging with Spatial-Temporal Analysis by FISH (VISTA-FISH), a technique that matches live-cell recordings of cultured cells with the expression of thousands of genes in the same cell at the end of the video. Moreover, VISTA-FISH can simultaneously detect CRISPR guide RNAs in pooled screens, enabling investigation into the fundamental underpinnings of cellular activity, organelle transport, and other pivotal cellular functions. Using VISTA-FISH, we measured gene expression and neuron activity in the same differentiating neurons. This combined single-cell transcriptomic and video data allowed us to link differentiation stage, subcellular transcript localization, and cell subtype with neuron activity. Using these measurements, we built a model to predict activity from expression. Finally, we performed a pooled CRISPR interference screen with live-cell lysosome imaging, identifying alterations in lysosome movement and morphology as well as gene expression in perturbed neurons. Collectively, these studies position VISTA-FISH as a powerful new tool for elucidating the molecular mechanisms underlying neuron activity, organelle trafficking, and other complex temporal phenotypes.