Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2426 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0282. Min Act: -0.0004

Data Index: 682676 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0277. Min Act: -0.0004

Data Index: 730425 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0263. Min Act: -0.0004

Data Index: 1340413 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0258. Min Act: -0.0004

Data Index: 392967 (C4 (Web Text))

Max Activating Token Index: 203

Text #4

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0245. Min Act: -0.0004

Data Index: 1029989 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0258. Min Act: -0.0004

Data Index: 508986 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0239. Min Act: -0.0004

Data Index: 436032 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0221. Min Act: -0.0004

Data Index: 1214839 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0221. Min Act: -0.0004

Data Index: 773048 (C4 (Web Text))

Max Activating Token Index: 679

Text #9

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0226. Min Act: -0.0004

Data Index: 168705 (C4 (Web Text))

Max Activating Token Index: 60

Text #10

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0215. Min Act: -0.0004

Data Index: 57082 (C4 (Web Text))

Max Activating Token Index: 413

Text #11

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0218. Min Act: -0.0004

Data Index: 412397 (C4 (Web Text))

Max Activating Token Index: 370

Text #12

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0208. Min Act: -0.0004

Data Index: 377388 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0210. Min Act: -0.0004

Data Index: 762920 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0208. Min Act: -0.0004

Data Index: 349234 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0202. Min Act: -0.0004

Data Index: 453515 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0206. Min Act: -0.0004

Data Index: 600144 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0205. Min Act: -0.0004

Data Index: 672687 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0171. Min Act: -0.0004

Data Index: 686526 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0194. Min Act: -0.0004

Data Index: 948768 (C4 (Web Text))

Max Activating Token Index: 691