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

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

Neuron 1231 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0372. Min Act: -0.0003

Data Index: 271118 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0366. Min Act: -0.0003

Data Index: 401260 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0359. Min Act: -0.0003

Data Index: 614667 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0361. Min Act: -0.0002

Data Index: 1423845 (Python Code)

Max Activating Token Index: 332

Text #4

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0349. Min Act: -0.0003

Data Index: 1057336 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0337. Min Act: -0.0002

Data Index: 1314594 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0337. Min Act: -0.0003

Data Index: 928093 (C4 (Web Text))

Max Activating Token Index: 375

Text #7

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0327. Min Act: -0.0002

Data Index: 555695 (C4 (Web Text))

Max Activating Token Index: 812

Text #8

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0325. Min Act: -0.0003

Data Index: 218481 (C4 (Web Text))

Max Activating Token Index: 171

Text #9

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0317. Min Act: -0.0003

Data Index: 1550843 (Python Code)

Max Activating Token Index: 221

Text #10

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0322. Min Act: -0.0003

Data Index: 122188 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0329. Min Act: -0.0002

Data Index: 1563797 (Python Code)

Max Activating Token Index: 191

Text #12

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0331. Min Act: -0.0002

Data Index: 1001990 (C4 (Web Text))

Max Activating Token Index: 690

Text #13

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0313. Min Act: -0.0003

Data Index: 643565 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0318. Min Act: -0.0003

Data Index: 1015697 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0310. Min Act: -0.0002

Data Index: 592347 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0315. Min Act: -0.0003

Data Index: 780689 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0323. Min Act: -0.0003

Data Index: 1525510 (Python Code)

Max Activating Token Index: 693

Text #18

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0308. Min Act: -0.0003

Data Index: 862871 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0311. Min Act: -0.0002

Data Index: 1140449 (C4 (Web Text))

Max Activating Token Index: 96