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

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

Neuron 1140 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: 0.0279. Min Range: -0.0279

Max Act: 0.0279. Min Act: -0.0002

Data Index: 1648335 (Python Code)

Max Activating Token Index: 920

Text #1

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0234. Min Act: -0.0002

Data Index: 1108015 (C4 (Web Text))

Max Activating Token Index: 502

Text #2

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0216. Min Act: -0.0002

Data Index: 449053 (C4 (Web Text))

Max Activating Token Index: 367

Text #3

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0210. Min Act: -0.0002

Data Index: 811361 (C4 (Web Text))

Max Activating Token Index: 271

Text #4

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0198. Min Act: -0.0002

Data Index: 1192316 (C4 (Web Text))

Max Activating Token Index: 655

Text #5

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0199. Min Act: -0.0002

Data Index: 1255696 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0196. Min Act: -0.0002

Data Index: 20245 (C4 (Web Text))

Max Activating Token Index: 553

Text #7

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0195. Min Act: -0.0002

Data Index: 154818 (C4 (Web Text))

Max Activating Token Index: 447

Text #8

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0192. Min Act: -0.0002

Data Index: 625397 (C4 (Web Text))

Max Activating Token Index: 359

Text #9

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0186. Min Act: -0.0002

Data Index: 1282744 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0189. Min Act: -0.0002

Data Index: 78106 (C4 (Web Text))

Max Activating Token Index: 263

Text #11

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0186. Min Act: -0.0002

Data Index: 872238 (C4 (Web Text))

Max Activating Token Index: 358

Text #12

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0182. Min Act: -0.0002

Data Index: 860656 (C4 (Web Text))

Max Activating Token Index: 279

Text #13

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0185. Min Act: -0.0002

Data Index: 548508 (C4 (Web Text))

Max Activating Token Index: 176

Text #14

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0181. Min Act: -0.0002

Data Index: 1259960 (C4 (Web Text))

Max Activating Token Index: 957

Text #15

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0180. Min Act: -0.0002

Data Index: 898768 (C4 (Web Text))

Max Activating Token Index: 158

Text #16

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0177. Min Act: -0.0002

Data Index: 857919 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0177. Min Act: -0.0002

Data Index: 691023 (C4 (Web Text))

Max Activating Token Index: 433

Text #18

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0177. Min Act: -0.0001

Data Index: 1482821 (Python Code)

Max Activating Token Index: 451

Text #19

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0171. Min Act: -0.0002

Data Index: 1233338 (C4 (Web Text))

Max Activating Token Index: 542