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

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

Neuron 3098 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0227. Min Act: -0.0002

Data Index: 537415 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0216. Min Act: -0.0002

Data Index: 194292 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0204. Min Act: -0.0002

Data Index: 1122311 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0206. Min Act: -0.0002

Data Index: 433760 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0200. Min Act: -0.0002

Data Index: 843834 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0201. Min Act: -0.0002

Data Index: 436046 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0201. Min Act: -0.0002

Data Index: 201532 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0202. Min Act: -0.0002

Data Index: 422999 (C4 (Web Text))

Max Activating Token Index: 303

Text #8

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0197. Min Act: -0.0002

Data Index: 147318 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0197. Min Act: -0.0002

Data Index: 30995 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0197. Min Act: -0.0002

Data Index: 714099 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0197. Min Act: -0.0002

Data Index: 1359557 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0196. Min Act: -0.0002

Data Index: 580058 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0196. Min Act: -0.0002

Data Index: 489209 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0195. Min Act: -0.0002

Data Index: 16864 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0194. Min Act: -0.0002

Data Index: 246699 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0193. Min Act: -0.0002

Data Index: 110867 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0188. Min Act: -0.0002

Data Index: 1061313 (C4 (Web Text))

Max Activating Token Index: 463

Text #18

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0192. Min Act: -0.0002

Data Index: 869561 (C4 (Web Text))

Max Activating Token Index: 176

Text #19

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0191. Min Act: -0.0002

Data Index: 201076 (C4 (Web Text))

Max Activating Token Index: 666