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

Dataset: The Pile

Neuron 941 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: 5.0244. Min Range: -5.0244

Max Act: 5.0244. Min Act: -0.0000

Data Index: 1449984 (The Pile)

Max Activating Token Index: 214

Text #1

Max Range: 5.0244. Min Range: -5.0244

Max Act: 3.8873. Min Act: -0.0000

Data Index: 1123275 (The Pile)

Max Activating Token Index: 619

Text #2

Max Range: 5.0244. Min Range: -5.0244

Max Act: 4.7142. Min Act: -0.0000

Data Index: 1126669 (The Pile)

Max Activating Token Index: 788

Text #3

Max Range: 5.0244. Min Range: -5.0244

Max Act: 4.6871. Min Act: -0.0000

Data Index: 1836840 (The Pile)

Max Activating Token Index: 277

Text #4

Max Range: 5.0244. Min Range: -5.0244

Max Act: 4.2014. Min Act: -0.0000

Data Index: 185511 (The Pile)

Max Activating Token Index: 637

Text #5

Max Range: 5.0244. Min Range: -5.0244

Max Act: 4.1820. Min Act: -0.0000

Data Index: 1906302 (The Pile)

Max Activating Token Index: 645

Text #6

Max Range: 5.0244. Min Range: -5.0244

Max Act: 4.7302. Min Act: -0.0000

Data Index: 185185 (The Pile)

Max Activating Token Index: 232

Text #7

Max Range: 5.0244. Min Range: -5.0244

Max Act: 3.8121. Min Act: -0.0000

Data Index: 1208629 (The Pile)

Max Activating Token Index: 770

Text #8

Max Range: 5.0244. Min Range: -5.0244

Max Act: 4.5458. Min Act: -0.0000

Data Index: 516604 (The Pile)

Max Activating Token Index: 968

Text #9

Max Range: 5.0244. Min Range: -5.0244

Max Act: 4.3518. Min Act: -0.0000

Data Index: 1164635 (The Pile)

Max Activating Token Index: 429

Text #10

Max Range: 5.0244. Min Range: -5.0244

Max Act: 4.1878. Min Act: -0.0000

Data Index: 1956075 (The Pile)

Max Activating Token Index: 928

Text #11

Max Range: 5.0244. Min Range: -5.0244

Max Act: 4.3154. Min Act: -0.0000

Data Index: 1855197 (The Pile)

Max Activating Token Index: 302

Text #12

Max Range: 5.0244. Min Range: -5.0244

Max Act: 4.3001. Min Act: -0.0000

Data Index: 140833 (The Pile)

Max Activating Token Index: 572

Text #13

Max Range: 5.0244. Min Range: -5.0244

Max Act: 4.3047. Min Act: -0.0000

Data Index: 374894 (The Pile)

Max Activating Token Index: 168

Text #14

Max Range: 5.0244. Min Range: -5.0244

Max Act: 4.1826. Min Act: -0.0000

Data Index: 982831 (The Pile)

Max Activating Token Index: 437

Text #15

Max Range: 5.0244. Min Range: -5.0244

Max Act: 4.0296. Min Act: -0.0000

Data Index: 399992 (The Pile)

Max Activating Token Index: 477

Text #16

Max Range: 5.0244. Min Range: -5.0244

Max Act: 4.0699. Min Act: -0.0000

Data Index: 476548 (The Pile)

Max Activating Token Index: 654

Text #17

Max Range: 5.0244. Min Range: -5.0244

Max Act: 4.1339. Min Act: -0.0000

Data Index: 1672507 (The Pile)

Max Activating Token Index: 810

Text #18

Max Range: 5.0244. Min Range: -5.0244

Max Act: 4.4225. Min Act: -0.0000

Data Index: 371164 (The Pile)

Max Activating Token Index: 262

Text #19

Max Range: 5.0244. Min Range: -5.0244

Max Act: 3.9534. Min Act: -0.0000

Data Index: 1771599 (The Pile)

Max Activating Token Index: 516