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

Dataset: The Pile

Neuron 4186 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: 1.0288. Min Range: -1.0288

Max Act: 1.0288. Min Act: -0.0000

Data Index: 1180172 (The Pile)

Max Activating Token Index: 491

Text #1

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.8789. Min Act: -0.0000

Data Index: 1683228 (The Pile)

Max Activating Token Index: 715

Text #2

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.8193. Min Act: -0.0000

Data Index: 899248 (The Pile)

Max Activating Token Index: 629

Text #3

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.7912. Min Act: -0.0000

Data Index: 1738270 (The Pile)

Max Activating Token Index: 1008

Text #4

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.6795. Min Act: -0.0000

Data Index: 1982887 (The Pile)

Max Activating Token Index: 770

Text #5

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.7114. Min Act: -0.0000

Data Index: 1774535 (The Pile)

Max Activating Token Index: 745

Text #6

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.7068. Min Act: -0.0000

Data Index: 1750913 (The Pile)

Max Activating Token Index: 839

Text #7

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.6504. Min Act: -0.0000

Data Index: 1031904 (The Pile)

Max Activating Token Index: 710

Text #8

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.6134. Min Act: -0.0000

Data Index: 1171979 (The Pile)

Max Activating Token Index: 568

Text #9

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.6283. Min Act: -0.0000

Data Index: 1819260 (The Pile)

Max Activating Token Index: 683

Text #10

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.6085. Min Act: -0.0000

Data Index: 1885039 (The Pile)

Max Activating Token Index: 429

Text #11

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.5772. Min Act: -0.0000

Data Index: 106038 (The Pile)

Max Activating Token Index: 1002

Text #12

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.5628. Min Act: -0.0000

Data Index: 294472 (The Pile)

Max Activating Token Index: 331

Text #13

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.6151. Min Act: -0.0000

Data Index: 984779 (The Pile)

Max Activating Token Index: 844

Text #14

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.5831. Min Act: -0.0000

Data Index: 1854334 (The Pile)

Max Activating Token Index: 579

Text #15

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.5543. Min Act: -0.0000

Data Index: 1091925 (The Pile)

Max Activating Token Index: 328

Text #16

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.5492. Min Act: -0.0000

Data Index: 3154 (The Pile)

Max Activating Token Index: 331

Text #17

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.5440. Min Act: -0.0000

Data Index: 1001943 (The Pile)

Max Activating Token Index: 618

Text #18

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.5401. Min Act: -0.0000

Data Index: 88643 (The Pile)

Max Activating Token Index: 966

Text #19

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.5412. Min Act: -0.0000

Data Index: 1397610 (The Pile)

Max Activating Token Index: 567