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

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

Neuron 4588 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.5270. Min Act: -0.0000

Data Index: 366713 (C4 (Web Text))

Max Activating Token Index: 424

Text #1

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.4894. Min Act: -0.0000

Data Index: 437421 (C4 (Web Text))

Max Activating Token Index: 872

Text #2

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.4215. Min Act: -0.0000

Data Index: 1357010 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.3975. Min Act: -0.0000

Data Index: 64484 (C4 (Web Text))

Max Activating Token Index: 452

Text #4

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.3795. Min Act: -0.0000

Data Index: 1251281 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.3662. Min Act: -0.0000

Data Index: 730838 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.3549. Min Act: -0.0000

Data Index: 169867 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.3407. Min Act: -0.0000

Data Index: 310338 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.3354. Min Act: -0.0000

Data Index: 1001091 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.3427. Min Act: -0.0000

Data Index: 1026203 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.3068. Min Act: -0.0000

Data Index: 1197978 (C4 (Web Text))

Max Activating Token Index: 1005

Text #11

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.3133. Min Act: -0.0000

Data Index: 6484 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.2929. Min Act: -0.0000

Data Index: 90970 (C4 (Web Text))

Max Activating Token Index: 989

Text #13

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.3106. Min Act: -0.0000

Data Index: 169342 (C4 (Web Text))

Max Activating Token Index: 235

Text #14

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.2989. Min Act: -0.0000

Data Index: 291709 (C4 (Web Text))

Max Activating Token Index: 477

Text #15

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.3169. Min Act: -0.0000

Data Index: 839425 (C4 (Web Text))

Max Activating Token Index: 926

Text #16

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.2847. Min Act: -0.0000

Data Index: 871491 (C4 (Web Text))

Max Activating Token Index: 363

Text #17

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.2719. Min Act: -0.0000

Data Index: 233179 (C4 (Web Text))

Max Activating Token Index: 831

Text #18

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.2803. Min Act: -0.0000

Data Index: 1072514 (C4 (Web Text))

Max Activating Token Index: 1004

Text #19

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.2452. Min Act: -0.0000

Data Index: 1284877 (C4 (Web Text))

Max Activating Token Index: 527