Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 905 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.6885. Min Act: -0.0000

Data Index: 1492549 (The Pile)

Max Activating Token Index: 688

Text #1

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.7603. Min Act: -0.0000

Data Index: 1033805 (The Pile)

Max Activating Token Index: 903

Text #2

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.8115. Min Act: -0.0000

Data Index: 1905448 (The Pile)

Max Activating Token Index: 1020

Text #3

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.7066. Min Act: -0.0000

Data Index: 425136 (The Pile)

Max Activating Token Index: 180

Text #4

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.8223. Min Act: -0.0000

Data Index: 442021 (The Pile)

Max Activating Token Index: 207

Text #5

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.8394. Min Act: -0.0000

Data Index: 1156225 (The Pile)

Max Activating Token Index: 390

Text #6

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.5262. Min Act: -0.0000

Data Index: 481256 (The Pile)

Max Activating Token Index: 373

Text #7

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.6044. Min Act: -0.0000

Data Index: 306996 (The Pile)

Max Activating Token Index: 883

Text #8

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.5520. Min Act: -0.0000

Data Index: 1351305 (The Pile)

Max Activating Token Index: 523

Text #9

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.4181. Min Act: -0.0000

Data Index: 1590636 (The Pile)

Max Activating Token Index: 605

Text #10

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.3516. Min Act: -0.0000

Data Index: 1759435 (The Pile)

Max Activating Token Index: 181

Text #11

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.4257. Min Act: -0.0000

Data Index: 1085079 (The Pile)

Max Activating Token Index: 253

Text #12

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.2868. Min Act: -0.0000

Data Index: 13646 (The Pile)

Max Activating Token Index: 938

Text #13

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.3199. Min Act: -0.0000

Data Index: 31779 (The Pile)

Max Activating Token Index: 851

Text #14

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.1713. Min Act: -0.0000

Data Index: 1978633 (The Pile)

Max Activating Token Index: 575

Text #15

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.3559. Min Act: -0.0000

Data Index: 1475457 (The Pile)

Max Activating Token Index: 492

Text #16

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.2657. Min Act: -0.0000

Data Index: 323588 (The Pile)

Max Activating Token Index: 714

Text #17

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.2049. Min Act: 0.0000

Data Index: 1634411 (The Pile)

Max Activating Token Index: 20

Text #18

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.1174. Min Act: -0.0000

Data Index: 913298 (The Pile)

Max Activating Token Index: 689

Text #19

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.2978. Min Act: -0.0000

Data Index: 878656 (The Pile)

Max Activating Token Index: 665