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

Dataset: The Pile

Neuron 2832 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: 5.7292. Min Range: -5.7292

Max Act: 5.5615. Min Act: -0.0000

Data Index: 1586087 (The Pile)

Max Activating Token Index: 563

Text #1

Max Range: 5.7292. Min Range: -5.7292

Max Act: 5.7292. Min Act: -0.0000

Data Index: 9383 (The Pile)

Max Activating Token Index: 419

Text #2

Max Range: 5.7292. Min Range: -5.7292

Max Act: 5.1306. Min Act: -0.0000

Data Index: 1494839 (The Pile)

Max Activating Token Index: 406

Text #3

Max Range: 5.7292. Min Range: -5.7292

Max Act: 5.1136. Min Act: -0.0000

Data Index: 625226 (The Pile)

Max Activating Token Index: 817

Text #4

Max Range: 5.7292. Min Range: -5.7292

Max Act: 4.5060. Min Act: -0.0000

Data Index: 1594513 (The Pile)

Max Activating Token Index: 1016

Text #5

Max Range: 5.7292. Min Range: -5.7292

Max Act: 4.5180. Min Act: -0.0000

Data Index: 130589 (The Pile)

Max Activating Token Index: 889

Text #6

Max Range: 5.7292. Min Range: -5.7292

Max Act: 4.5889. Min Act: -0.0000

Data Index: 503082 (The Pile)

Max Activating Token Index: 1010

Text #7

Max Range: 5.7292. Min Range: -5.7292

Max Act: 4.2426. Min Act: -0.0000

Data Index: 976034 (The Pile)

Max Activating Token Index: 951

Text #8

Max Range: 5.7292. Min Range: -5.7292

Max Act: 3.8875. Min Act: -0.0000

Data Index: 1266344 (The Pile)

Max Activating Token Index: 870

Text #9

Max Range: 5.7292. Min Range: -5.7292

Max Act: 4.2305. Min Act: -0.0000

Data Index: 1770539 (The Pile)

Max Activating Token Index: 262

Text #10

Max Range: 5.7292. Min Range: -5.7292

Max Act: 3.9252. Min Act: -0.0000

Data Index: 862793 (The Pile)

Max Activating Token Index: 381

Text #11

Max Range: 5.7292. Min Range: -5.7292

Max Act: 3.7292. Min Act: -0.0000

Data Index: 1231697 (The Pile)

Max Activating Token Index: 219

Text #12

Max Range: 5.7292. Min Range: -5.7292

Max Act: 4.2292. Min Act: -0.0000

Data Index: 1963273 (The Pile)

Max Activating Token Index: 382

Text #13

Max Range: 5.7292. Min Range: -5.7292

Max Act: 4.0365. Min Act: -0.0000

Data Index: 1570144 (The Pile)

Max Activating Token Index: 738

Text #14

Max Range: 5.7292. Min Range: -5.7292

Max Act: 3.9713. Min Act: -0.0000

Data Index: 1904593 (The Pile)

Max Activating Token Index: 38

Text #15

Max Range: 5.7292. Min Range: -5.7292

Max Act: 4.0284. Min Act: -0.0000

Data Index: 494914 (The Pile)

Max Activating Token Index: 431

Text #16

Max Range: 5.7292. Min Range: -5.7292

Max Act: 3.9204. Min Act: -0.0000

Data Index: 299186 (The Pile)

Max Activating Token Index: 540

Text #17

Max Range: 5.7292. Min Range: -5.7292

Max Act: 3.9189. Min Act: -0.0000

Data Index: 670506 (The Pile)

Max Activating Token Index: 125

Text #18

Max Range: 5.7292. Min Range: -5.7292

Max Act: 3.8589. Min Act: -0.0000

Data Index: 1709150 (The Pile)

Max Activating Token Index: 996

Text #19

Max Range: 5.7292. Min Range: -5.7292

Max Act: 4.0601. Min Act: -0.0000

Data Index: 1120081 (The Pile)

Max Activating Token Index: 926