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

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

Neuron 3688 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4417. Min Range: -0.4417

Max Act: 0.4417. Min Act: -0.0000

Data Index: 447320 (C4 (Web Text))

Max Activating Token Index: 451

Text #1

Max Range: 0.4417. Min Range: -0.4417

Max Act: 0.3733. Min Act: -0.0000

Data Index: 308650 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 0.4417. Min Range: -0.4417

Max Act: 0.3642. Min Act: -0.0000

Data Index: 1305217 (C4 (Web Text))

Max Activating Token Index: 481

Text #3

Max Range: 0.4417. Min Range: -0.4417

Max Act: 0.3371. Min Act: -0.0000

Data Index: 455936 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 0.4417. Min Range: -0.4417

Max Act: 0.3552. Min Act: -0.0000

Data Index: 1342988 (C4 (Web Text))

Max Activating Token Index: 170

Text #5

Max Range: 0.4417. Min Range: -0.4417

Max Act: 0.3317. Min Act: -0.0000

Data Index: 250698 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 0.4417. Min Range: -0.4417

Max Act: 0.3384. Min Act: -0.0000

Data Index: 490246 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 0.4417. Min Range: -0.4417

Max Act: 0.3293. Min Act: -0.0000

Data Index: 1241969 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 0.4417. Min Range: -0.4417

Max Act: 0.3084. Min Act: -0.0000

Data Index: 312968 (C4 (Web Text))

Max Activating Token Index: 384

Text #9

Max Range: 0.4417. Min Range: -0.4417

Max Act: 0.2915. Min Act: -0.0000

Data Index: 845330 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 0.4417. Min Range: -0.4417

Max Act: 0.3186. Min Act: -0.0000

Data Index: 442530 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 0.4417. Min Range: -0.4417

Max Act: 0.3245. Min Act: -0.0000

Data Index: 193467 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 0.4417. Min Range: -0.4417

Max Act: 0.3205. Min Act: -0.0000

Data Index: 1333736 (C4 (Web Text))

Max Activating Token Index: 788

Text #13

Max Range: 0.4417. Min Range: -0.4417

Max Act: 0.2859. Min Act: -0.0000

Data Index: 2146 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 0.4417. Min Range: -0.4417

Max Act: 0.3070. Min Act: -0.0000

Data Index: 157596 (C4 (Web Text))

Max Activating Token Index: 134

Text #15

Max Range: 0.4417. Min Range: -0.4417

Max Act: 0.3077. Min Act: -0.0000

Data Index: 1162987 (C4 (Web Text))

Max Activating Token Index: 662

Text #16

Max Range: 0.4417. Min Range: -0.4417

Max Act: 0.3100. Min Act: -0.0000

Data Index: 808966 (C4 (Web Text))

Max Activating Token Index: 708

Text #17

Max Range: 0.4417. Min Range: -0.4417

Max Act: 0.2841. Min Act: -0.0000

Data Index: 1218555 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 0.4417. Min Range: -0.4417

Max Act: 0.3277. Min Act: -0.0000

Data Index: 849594 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 0.4417. Min Range: -0.4417

Max Act: 0.2942. Min Act: -0.0000

Data Index: 849590 (C4 (Web Text))

Max Activating Token Index: 727