Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 966 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0362. Min Act: -0.0002

Data Index: 429404 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0367. Min Act: -0.0002

Data Index: 619263 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0355. Min Act: -0.0002

Data Index: 44183 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0346. Min Act: -0.0002

Data Index: 1060396 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0357. Min Act: -0.0002

Data Index: 971459 (C4 (Web Text))

Max Activating Token Index: 1006

Text #5

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0333. Min Act: -0.0002

Data Index: 250051 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0333. Min Act: -0.0002

Data Index: 677598 (C4 (Web Text))

Max Activating Token Index: 757

Text #7

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0329. Min Act: -0.0002

Data Index: 875729 (C4 (Web Text))

Max Activating Token Index: 336

Text #8

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0335. Min Act: -0.0002

Data Index: 855471 (C4 (Web Text))

Max Activating Token Index: 655

Text #9

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0322. Min Act: -0.0002

Data Index: 121503 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0320. Min Act: -0.0002

Data Index: 591899 (C4 (Web Text))

Max Activating Token Index: 122

Text #11

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0327. Min Act: -0.0002

Data Index: 228706 (C4 (Web Text))

Max Activating Token Index: 887

Text #12

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0313. Min Act: -0.0002

Data Index: 1239957 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0321. Min Act: -0.0002

Data Index: 798353 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0308. Min Act: -0.0002

Data Index: 299271 (C4 (Web Text))

Max Activating Token Index: 410

Text #15

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0327. Min Act: -0.0002

Data Index: 84267 (C4 (Web Text))

Max Activating Token Index: 532

Text #16

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0306. Min Act: -0.0002

Data Index: 333334 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0311. Min Act: -0.0002

Data Index: 481304 (C4 (Web Text))

Max Activating Token Index: 303

Text #18

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0306. Min Act: -0.0002

Data Index: 1135102 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0308. Min Act: -0.0002

Data Index: 372032 (C4 (Web Text))

Max Activating Token Index: 205