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

Dataset: The Pile

Neuron 3488 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.7209. Min Act: -0.0000

Data Index: 191402 (The Pile)

Max Activating Token Index: 28

Text #1

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.6445. Min Act: -0.0000

Data Index: 1811672 (The Pile)

Max Activating Token Index: 658

Text #2

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.6227. Min Act: -0.0000

Data Index: 81141 (The Pile)

Max Activating Token Index: 198

Text #3

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.6180. Min Act: -0.0000

Data Index: 505612 (The Pile)

Max Activating Token Index: 797

Text #4

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.5958. Min Act: -0.0000

Data Index: 1352939 (The Pile)

Max Activating Token Index: 70

Text #5

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.5880. Min Act: 0.0000

Data Index: 1525041 (The Pile)

Max Activating Token Index: 172

Text #6

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.5875. Min Act: -0.0000

Data Index: 694358 (The Pile)

Max Activating Token Index: 493

Text #7

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.5536. Min Act: -0.0000

Data Index: 562971 (The Pile)

Max Activating Token Index: 30

Text #8

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.5950. Min Act: -0.0000

Data Index: 236234 (The Pile)

Max Activating Token Index: 596

Text #9

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.5441. Min Act: 0.0000

Data Index: 1204428 (The Pile)

Max Activating Token Index: 476

Text #10

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.5441. Min Act: -0.0000

Data Index: 1818978 (The Pile)

Max Activating Token Index: 331

Text #11

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.5369. Min Act: 0.0000

Data Index: 1373457 (The Pile)

Max Activating Token Index: 315

Text #12

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.5516. Min Act: 0.0000

Data Index: 1366558 (The Pile)

Max Activating Token Index: 269

Text #13

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.5266. Min Act: -0.0000

Data Index: 72240 (The Pile)

Max Activating Token Index: 222

Text #14

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.5632. Min Act: -0.0000

Data Index: 1397130 (The Pile)

Max Activating Token Index: 393

Text #15

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.5526. Min Act: -0.0000

Data Index: 1930754 (The Pile)

Max Activating Token Index: 930

Text #16

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.5272. Min Act: -0.0000

Data Index: 226048 (The Pile)

Max Activating Token Index: 5

Text #17

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.5390. Min Act: -0.0000

Data Index: 1459364 (The Pile)

Max Activating Token Index: 491

Text #18

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.5361. Min Act: -0.0000

Data Index: 1288510 (The Pile)

Max Activating Token Index: 71

Text #19

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.5522. Min Act: -0.0000

Data Index: 1660971 (The Pile)

Max Activating Token Index: 172