Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4496 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.9591. Min Range: -0.9591

Max Act: 0.8865. Min Act: -0.0000

Data Index: 936020 (The Pile)

Max Activating Token Index: 52

Text #1

Max Range: 0.9591. Min Range: -0.9591

Max Act: 0.8551. Min Act: -0.0000

Data Index: 280310 (The Pile)

Max Activating Token Index: 323

Text #2

Max Range: 0.9591. Min Range: -0.9591

Max Act: 0.9591. Min Act: -0.0000

Data Index: 420725 (The Pile)

Max Activating Token Index: 208

Text #3

Max Range: 0.9591. Min Range: -0.9591

Max Act: 0.8479. Min Act: -0.0000

Data Index: 471653 (The Pile)

Max Activating Token Index: 254

Text #4

Max Range: 0.9591. Min Range: -0.9591

Max Act: 0.7844. Min Act: -0.0000

Data Index: 721932 (The Pile)

Max Activating Token Index: 329

Text #5

Max Range: 0.9591. Min Range: -0.9591

Max Act: 0.7805. Min Act: -0.0000

Data Index: 1946137 (The Pile)

Max Activating Token Index: 31

Text #6

Max Range: 0.9591. Min Range: -0.9591

Max Act: 0.7350. Min Act: -0.0000

Data Index: 1290919 (The Pile)

Max Activating Token Index: 317

Text #7

Max Range: 0.9591. Min Range: -0.9591

Max Act: 0.8406. Min Act: -0.0000

Data Index: 1565212 (The Pile)

Max Activating Token Index: 103

Text #8

Max Range: 0.9591. Min Range: -0.9591

Max Act: 0.7979. Min Act: -0.0000

Data Index: 1181278 (The Pile)

Max Activating Token Index: 109

Text #9

Max Range: 0.9591. Min Range: -0.9591

Max Act: 0.7942. Min Act: -0.0000

Data Index: 1813264 (The Pile)

Max Activating Token Index: 294

Text #10

Max Range: 0.9591. Min Range: -0.9591

Max Act: 0.7090. Min Act: -0.0000

Data Index: 819167 (The Pile)

Max Activating Token Index: 796

Text #11

Max Range: 0.9591. Min Range: -0.9591

Max Act: 0.7389. Min Act: -0.0000

Data Index: 1451431 (The Pile)

Max Activating Token Index: 306

Text #12

Max Range: 0.9591. Min Range: -0.9591

Max Act: 0.7697. Min Act: -0.0000

Data Index: 271466 (The Pile)

Max Activating Token Index: 507

Text #13

Max Range: 0.9591. Min Range: -0.9591

Max Act: 0.7044. Min Act: -0.0000

Data Index: 1727935 (The Pile)

Max Activating Token Index: 546

Text #14

Max Range: 0.9591. Min Range: -0.9591

Max Act: 0.6888. Min Act: -0.0000

Data Index: 353306 (The Pile)

Max Activating Token Index: 50

Text #15

Max Range: 0.9591. Min Range: -0.9591

Max Act: 0.6962. Min Act: -0.0000

Data Index: 1240310 (The Pile)

Max Activating Token Index: 163

Text #16

Max Range: 0.9591. Min Range: -0.9591

Max Act: 0.7768. Min Act: -0.0000

Data Index: 791345 (The Pile)

Max Activating Token Index: 797

Text #17

Max Range: 0.9591. Min Range: -0.9591

Max Act: 0.6748. Min Act: -0.0000

Data Index: 1212846 (The Pile)

Max Activating Token Index: 143

Text #18

Max Range: 0.9591. Min Range: -0.9591

Max Act: 0.7127. Min Act: -0.0000

Data Index: 1817655 (The Pile)

Max Activating Token Index: 135

Text #19

Max Range: 0.9591. Min Range: -0.9591

Max Act: 0.6840. Min Act: -0.0000

Data Index: 1894446 (The Pile)

Max Activating Token Index: 906