Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 281 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0234. Min Act: -0.0004

Data Index: 102366 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0208. Min Act: -0.0004

Data Index: 843453 (C4 (Web Text))

Max Activating Token Index: 317

Text #2

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0206. Min Act: -0.0005

Data Index: 419587 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0205. Min Act: -0.0004

Data Index: 756072 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0202. Min Act: -0.0004

Data Index: 851376 (C4 (Web Text))

Max Activating Token Index: 177

Text #5

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0201. Min Act: -0.0004

Data Index: 1207703 (C4 (Web Text))

Max Activating Token Index: 965

Text #6

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0193. Min Act: -0.0004

Data Index: 41869 (C4 (Web Text))

Max Activating Token Index: 484

Text #7

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0196. Min Act: -0.0004

Data Index: 1227666 (C4 (Web Text))

Max Activating Token Index: 454

Text #8

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0196. Min Act: -0.0004

Data Index: 440706 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0196. Min Act: -0.0004

Data Index: 592037 (C4 (Web Text))

Max Activating Token Index: 523

Text #10

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0191. Min Act: -0.0004

Data Index: 825172 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0194. Min Act: -0.0004

Data Index: 946651 (C4 (Web Text))

Max Activating Token Index: 480

Text #12

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0193. Min Act: -0.0004

Data Index: 1338458 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0188. Min Act: -0.0004

Data Index: 1014527 (C4 (Web Text))

Max Activating Token Index: 956

Text #14

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0186. Min Act: -0.0004

Data Index: 285212 (C4 (Web Text))

Max Activating Token Index: 908

Text #15

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0186. Min Act: -0.0004

Data Index: 605884 (C4 (Web Text))

Max Activating Token Index: 653

Text #16

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0185. Min Act: -0.0004

Data Index: 737861 (C4 (Web Text))

Max Activating Token Index: 932

Text #17

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0185. Min Act: -0.0005

Data Index: 635269 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0183. Min Act: -0.0004

Data Index: 374404 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0183. Min Act: -0.0004

Data Index: 766255 (C4 (Web Text))

Max Activating Token Index: 383