Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3667 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.4097. Min Act: -0.0000

Data Index: 577402 (C4 (Web Text))

Max Activating Token Index: 765

Text #1

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.3687. Min Act: -0.0000

Data Index: 1092967 (C4 (Web Text))

Max Activating Token Index: 438

Text #2

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.3355. Min Act: -0.0000

Data Index: 643258 (C4 (Web Text))

Max Activating Token Index: 710

Text #3

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.3578. Min Act: -0.0000

Data Index: 908507 (C4 (Web Text))

Max Activating Token Index: 821

Text #4

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.3440. Min Act: -0.0000

Data Index: 583172 (C4 (Web Text))

Max Activating Token Index: 814

Text #5

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.3511. Min Act: -0.0000

Data Index: 836089 (C4 (Web Text))

Max Activating Token Index: 383

Text #6

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.3445. Min Act: -0.0000

Data Index: 229740 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.3439. Min Act: -0.0000

Data Index: 1266444 (C4 (Web Text))

Max Activating Token Index: 368

Text #8

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.3278. Min Act: -0.0000

Data Index: 913361 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.3177. Min Act: -0.0000

Data Index: 890401 (C4 (Web Text))

Max Activating Token Index: 304

Text #10

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.3096. Min Act: -0.0000

Data Index: 333999 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.3306. Min Act: -0.0000

Data Index: 327839 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.3390. Min Act: -0.0000

Data Index: 994182 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2987. Min Act: -0.0001

Data Index: 1208480 (C4 (Web Text))

Max Activating Token Index: 359

Text #14

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.3268. Min Act: -0.0000

Data Index: 96835 (C4 (Web Text))

Max Activating Token Index: 1019

Text #15

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.3120. Min Act: -0.0000

Data Index: 44775 (C4 (Web Text))

Max Activating Token Index: 994

Text #16

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.3028. Min Act: -0.0000

Data Index: 447209 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2831. Min Act: -0.0001

Data Index: 191700 (C4 (Web Text))

Max Activating Token Index: 793

Text #18

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2905. Min Act: -0.0001

Data Index: 444077 (C4 (Web Text))

Max Activating Token Index: 661

Text #19

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.3108. Min Act: -0.0000

Data Index: 91703 (C4 (Web Text))

Max Activating Token Index: 252