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

Dataset: The Pile

Neuron 1093 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.9121. Min Act: -0.0000

Data Index: 1221205 (The Pile)

Max Activating Token Index: 62

Text #1

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.5352. Min Act: -0.0000

Data Index: 5697 (The Pile)

Max Activating Token Index: 85

Text #2

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.4224. Min Act: -0.0000

Data Index: 273560 (The Pile)

Max Activating Token Index: 889

Text #3

Max Range: 3.9121. Min Range: -3.9121

Max Act: 2.6486. Min Act: -0.0000

Data Index: 1335737 (The Pile)

Max Activating Token Index: 619

Text #4

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.1511. Min Act: -0.0000

Data Index: 908288 (The Pile)

Max Activating Token Index: 432

Text #5

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.2222. Min Act: -0.0000

Data Index: 1493658 (The Pile)

Max Activating Token Index: 787

Text #6

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.0521. Min Act: -0.0000

Data Index: 1052975 (The Pile)

Max Activating Token Index: 621

Text #7

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.1473. Min Act: -0.0000

Data Index: 536708 (The Pile)

Max Activating Token Index: 696

Text #8

Max Range: 3.9121. Min Range: -3.9121

Max Act: 2.7872. Min Act: -0.0000

Data Index: 707057 (The Pile)

Max Activating Token Index: 370

Text #9

Max Range: 3.9121. Min Range: -3.9121

Max Act: 2.7520. Min Act: -0.0000

Data Index: 754473 (The Pile)

Max Activating Token Index: 100

Text #10

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.0148. Min Act: -0.0000

Data Index: 1716359 (The Pile)

Max Activating Token Index: 160

Text #11

Max Range: 3.9121. Min Range: -3.9121

Max Act: 2.8475. Min Act: -0.0000

Data Index: 580216 (The Pile)

Max Activating Token Index: 923

Text #12

Max Range: 3.9121. Min Range: -3.9121

Max Act: 2.5354. Min Act: -0.0000

Data Index: 1660755 (The Pile)

Max Activating Token Index: 148

Text #13

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.0661. Min Act: -0.0000

Data Index: 314151 (The Pile)

Max Activating Token Index: 694

Text #14

Max Range: 3.9121. Min Range: -3.9121

Max Act: 2.7699. Min Act: -0.0000

Data Index: 1867485 (The Pile)

Max Activating Token Index: 971

Text #15

Max Range: 3.9121. Min Range: -3.9121

Max Act: 2.6174. Min Act: -0.0000

Data Index: 1526412 (The Pile)

Max Activating Token Index: 672

Text #16

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.0368. Min Act: -0.0000

Data Index: 460566 (The Pile)

Max Activating Token Index: 697

Text #17

Max Range: 3.9121. Min Range: -3.9121

Max Act: 2.7173. Min Act: -0.0000

Data Index: 787963 (The Pile)

Max Activating Token Index: 983

Text #18

Max Range: 3.9121. Min Range: -3.9121

Max Act: 2.8245. Min Act: -0.0000

Data Index: 1613520 (The Pile)

Max Activating Token Index: 227

Text #19

Max Range: 3.9121. Min Range: -3.9121

Max Act: 2.5890. Min Act: -0.0000

Data Index: 122115 (The Pile)

Max Activating Token Index: 473