Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1393 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0440. Min Act: -0.0003

Data Index: 58522 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0400. Min Act: -0.0003

Data Index: 69609 (C4 (Web Text))

Max Activating Token Index: 865

Text #2

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0382. Min Act: -0.0003

Data Index: 1406933 (Python Code)

Max Activating Token Index: 119

Text #3

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0368. Min Act: -0.0003

Data Index: 866058 (C4 (Web Text))

Max Activating Token Index: 629

Text #4

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0368. Min Act: -0.0003

Data Index: 325061 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0361. Min Act: -0.0003

Data Index: 727711 (C4 (Web Text))

Max Activating Token Index: 432

Text #6

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0363. Min Act: -0.0003

Data Index: 891929 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0359. Min Act: -0.0003

Data Index: 440954 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0370. Min Act: -0.0003

Data Index: 489083 (C4 (Web Text))

Max Activating Token Index: 945

Text #9

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0347. Min Act: -0.0003

Data Index: 681851 (C4 (Web Text))

Max Activating Token Index: 138

Text #10

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0364. Min Act: -0.0003

Data Index: 783972 (C4 (Web Text))

Max Activating Token Index: 464

Text #11

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0361. Min Act: -0.0003

Data Index: 1611989 (Python Code)

Max Activating Token Index: 898

Text #12

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0359. Min Act: -0.0003

Data Index: 619596 (C4 (Web Text))

Max Activating Token Index: 469

Text #13

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0380. Min Act: -0.0003

Data Index: 279262 (C4 (Web Text))

Max Activating Token Index: 881

Text #14

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0344. Min Act: -0.0003

Data Index: 232326 (C4 (Web Text))

Max Activating Token Index: 493

Text #15

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0344. Min Act: -0.0003

Data Index: 80621 (C4 (Web Text))

Max Activating Token Index: 758

Text #16

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0356. Min Act: -0.0003

Data Index: 527757 (C4 (Web Text))

Max Activating Token Index: 413

Text #17

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0346. Min Act: -0.0003

Data Index: 542965 (C4 (Web Text))

Max Activating Token Index: 907

Text #18

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0332. Min Act: -0.0003

Data Index: 535275 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0325. Min Act: -0.0003

Data Index: 1107444 (C4 (Web Text))

Max Activating Token Index: 354