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

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

Neuron 4756 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0412. Min Act: -0.0002

Data Index: 1464766 (Python Code)

Max Activating Token Index: 412

Text #1

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0369. Min Act: -0.0002

Data Index: 848037 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0340. Min Act: -0.0002

Data Index: 417491 (C4 (Web Text))

Max Activating Token Index: 617

Text #3

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0358. Min Act: -0.0002

Data Index: 903344 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0357. Min Act: -0.0002

Data Index: 153431 (C4 (Web Text))

Max Activating Token Index: 144

Text #5

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0354. Min Act: -0.0002

Data Index: 962389 (C4 (Web Text))

Max Activating Token Index: 177

Text #6

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0315. Min Act: -0.0002

Data Index: 572038 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0332. Min Act: -0.0002

Data Index: 918917 (C4 (Web Text))

Max Activating Token Index: 561

Text #8

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0353. Min Act: -0.0002

Data Index: 433348 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0354. Min Act: -0.0002

Data Index: 977493 (C4 (Web Text))

Max Activating Token Index: 336

Text #10

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0318. Min Act: -0.0002

Data Index: 1014796 (C4 (Web Text))

Max Activating Token Index: 574

Text #11

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0333. Min Act: -0.0002

Data Index: 677936 (C4 (Web Text))

Max Activating Token Index: 604

Text #12

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0332. Min Act: -0.0002

Data Index: 1347273 (C4 (Web Text))

Max Activating Token Index: 94

Text #13

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0326. Min Act: -0.0002

Data Index: 310602 (C4 (Web Text))

Max Activating Token Index: 156

Text #14

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0337. Min Act: -0.0002

Data Index: 21721 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0344. Min Act: -0.0002

Data Index: 907338 (C4 (Web Text))

Max Activating Token Index: 141

Text #16

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0292. Min Act: -0.0002

Data Index: 1227082 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0332. Min Act: -0.0002

Data Index: 379779 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0307. Min Act: -0.0002

Data Index: 1032436 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0310. Min Act: -0.0002

Data Index: 582956 (C4 (Web Text))

Max Activating Token Index: 413