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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3986 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3326. Min Range: -1.3326

Max Act: 1.3326. Min Act: -0.0000

Data Index: 446938 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 1.3326. Min Range: -1.3326

Max Act: 1.1868. Min Act: -0.0000

Data Index: 449828 (C4 (Web Text))

Max Activating Token Index: 467

Text #2

Max Range: 1.3326. Min Range: -1.3326

Max Act: 1.1599. Min Act: -0.0000

Data Index: 168237 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 1.3326. Min Range: -1.3326

Max Act: 1.0547. Min Act: -0.0000

Data Index: 311019 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 1.3326. Min Range: -1.3326

Max Act: 0.9246. Min Act: -0.0000

Data Index: 758752 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 1.3326. Min Range: -1.3326

Max Act: 0.9881. Min Act: -0.0000

Data Index: 315617 (C4 (Web Text))

Max Activating Token Index: 639

Text #6

Max Range: 1.3326. Min Range: -1.3326

Max Act: 0.9275. Min Act: -0.0000

Data Index: 689850 (C4 (Web Text))

Max Activating Token Index: 918

Text #7

Max Range: 1.3326. Min Range: -1.3326

Max Act: 0.9626. Min Act: -0.0000

Data Index: 1134347 (C4 (Web Text))

Max Activating Token Index: 710

Text #8

Max Range: 1.3326. Min Range: -1.3326

Max Act: 0.9000. Min Act: -0.0000

Data Index: 582857 (C4 (Web Text))

Max Activating Token Index: 664

Text #9

Max Range: 1.3326. Min Range: -1.3326

Max Act: 0.8492. Min Act: -0.0000

Data Index: 320358 (C4 (Web Text))

Max Activating Token Index: 254

Text #10

Max Range: 1.3326. Min Range: -1.3326

Max Act: 0.9190. Min Act: -0.0000

Data Index: 56579 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 1.3326. Min Range: -1.3326

Max Act: 0.8918. Min Act: -0.0000

Data Index: 684529 (C4 (Web Text))

Max Activating Token Index: 932

Text #12

Max Range: 1.3326. Min Range: -1.3326

Max Act: 0.7971. Min Act: -0.0000

Data Index: 881370 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 1.3326. Min Range: -1.3326

Max Act: 0.8896. Min Act: -0.0000

Data Index: 1543260 (Python Code)

Max Activating Token Index: 272

Text #14

Max Range: 1.3326. Min Range: -1.3326

Max Act: 0.8749. Min Act: -0.0000

Data Index: 24573 (C4 (Web Text))

Max Activating Token Index: 763

Text #15

Max Range: 1.3326. Min Range: -1.3326

Max Act: 0.8164. Min Act: -0.0000

Data Index: 341517 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 1.3326. Min Range: -1.3326

Max Act: 0.9202. Min Act: -0.0000

Data Index: 1145089 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 1.3326. Min Range: -1.3326

Max Act: 0.8581. Min Act: -0.0000

Data Index: 1264628 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 1.3326. Min Range: -1.3326

Max Act: 0.8565. Min Act: -0.0000

Data Index: 861866 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 1.3326. Min Range: -1.3326

Max Act: 0.8849. Min Act: -0.0000

Data Index: 1200980 (C4 (Web Text))

Max Activating Token Index: 120