Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1432 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0520. Min Act: -0.0006

Data Index: 252711 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0472. Min Act: -0.0006

Data Index: 184602 (C4 (Web Text))

Max Activating Token Index: 888

Text #2

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0439. Min Act: -0.0006

Data Index: 236813 (C4 (Web Text))

Max Activating Token Index: 866

Text #3

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0438. Min Act: -0.0006

Data Index: 750187 (C4 (Web Text))

Max Activating Token Index: 1020

Text #4

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0424. Min Act: -0.0006

Data Index: 421999 (C4 (Web Text))

Max Activating Token Index: 967

Text #5

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0401. Min Act: -0.0006

Data Index: 215853 (C4 (Web Text))

Max Activating Token Index: 910

Text #6

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0376. Min Act: -0.0006

Data Index: 1140189 (C4 (Web Text))

Max Activating Token Index: 685

Text #7

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0360. Min Act: -0.0006

Data Index: 1121976 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0370. Min Act: -0.0006

Data Index: 1340498 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0366. Min Act: -0.0006

Data Index: 1102988 (C4 (Web Text))

Max Activating Token Index: 834

Text #10

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0374. Min Act: -0.0006

Data Index: 501772 (C4 (Web Text))

Max Activating Token Index: 617

Text #11

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0361. Min Act: -0.0006

Data Index: 226069 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0359. Min Act: -0.0006

Data Index: 143502 (C4 (Web Text))

Max Activating Token Index: 1005

Text #13

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0355. Min Act: -0.0006

Data Index: 361579 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0326. Min Act: -0.0006

Data Index: 307127 (C4 (Web Text))

Max Activating Token Index: 699

Text #15

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0353. Min Act: -0.0006

Data Index: 1245456 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0352. Min Act: -0.0006

Data Index: 492509 (C4 (Web Text))

Max Activating Token Index: 867

Text #17

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0357. Min Act: -0.0006

Data Index: 1066273 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0337. Min Act: -0.0006

Data Index: 299390 (C4 (Web Text))

Max Activating Token Index: 843

Text #19

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0349. Min Act: -0.0006

Data Index: 394517 (C4 (Web Text))

Max Activating Token Index: 758