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

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

Neuron 3587 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0255. Min Act: -0.0002

Data Index: 53342 (C4 (Web Text))

Max Activating Token Index: 698

Text #1

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0260. Min Act: -0.0002

Data Index: 458977 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0243. Min Act: -0.0002

Data Index: 324580 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0222. Min Act: -0.0002

Data Index: 736540 (C4 (Web Text))

Max Activating Token Index: 677

Text #4

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0231. Min Act: -0.0002

Data Index: 141971 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0234. Min Act: -0.0002

Data Index: 961024 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0222. Min Act: -0.0002

Data Index: 978513 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0227. Min Act: -0.0002

Data Index: 872465 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0221. Min Act: -0.0002

Data Index: 1070417 (C4 (Web Text))

Max Activating Token Index: 719

Text #9

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0221. Min Act: -0.0002

Data Index: 235402 (C4 (Web Text))

Max Activating Token Index: 883

Text #10

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0221. Min Act: -0.0002

Data Index: 1284109 (C4 (Web Text))

Max Activating Token Index: 621

Text #11

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0223. Min Act: -0.0002

Data Index: 1165050 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0210. Min Act: -0.0002

Data Index: 661179 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0219. Min Act: -0.0002

Data Index: 646680 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0210. Min Act: -0.0002

Data Index: 641662 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0225. Min Act: -0.0002

Data Index: 699622 (C4 (Web Text))

Max Activating Token Index: 6

Text #16

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0223. Min Act: -0.0002

Data Index: 877749 (C4 (Web Text))

Max Activating Token Index: 65

Text #17

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0207. Min Act: -0.0002

Data Index: 989696 (C4 (Web Text))

Max Activating Token Index: 677

Text #18

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0216. Min Act: -0.0002

Data Index: 604108 (C4 (Web Text))

Max Activating Token Index: 3

Text #19

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0196. Min Act: -0.0002

Data Index: 1337252 (C4 (Web Text))

Max Activating Token Index: 646