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

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

Neuron 1503 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: 0.0279. Min Range: -0.0279

Max Act: 0.0257. Min Act: -0.0002

Data Index: 382647 (C4 (Web Text))

Max Activating Token Index: 234

Text #1

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0273. Min Act: -0.0002

Data Index: 6446 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0279. Min Act: -0.0002

Data Index: 924860 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0276. Min Act: -0.0002

Data Index: 154615 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0254. Min Act: -0.0002

Data Index: 1511992 (Python Code)

Max Activating Token Index: 94

Text #5

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0249. Min Act: -0.0002

Data Index: 660907 (C4 (Web Text))

Max Activating Token Index: 657

Text #6

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0265. Min Act: -0.0002

Data Index: 1234233 (C4 (Web Text))

Max Activating Token Index: 684

Text #7

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0264. Min Act: -0.0002

Data Index: 287689 (C4 (Web Text))

Max Activating Token Index: 507

Text #8

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0231. Min Act: -0.0002

Data Index: 1538605 (Python Code)

Max Activating Token Index: 99

Text #9

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0236. Min Act: -0.0002

Data Index: 1179955 (C4 (Web Text))

Max Activating Token Index: 654

Text #10

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0239. Min Act: -0.0002

Data Index: 644556 (C4 (Web Text))

Max Activating Token Index: 924

Text #11

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0243. Min Act: -0.0002

Data Index: 1190529 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0225. Min Act: -0.0002

Data Index: 1653561 (Python Code)

Max Activating Token Index: 163

Text #13

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0228. Min Act: -0.0002

Data Index: 409319 (C4 (Web Text))

Max Activating Token Index: 549

Text #14

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0214. Min Act: -0.0002

Data Index: 1426414 (Python Code)

Max Activating Token Index: 891

Text #15

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0228. Min Act: -0.0002

Data Index: 559874 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0232. Min Act: -0.0002

Data Index: 1391563 (Python Code)

Max Activating Token Index: 277

Text #17

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0218. Min Act: -0.0002

Data Index: 1638075 (Python Code)

Max Activating Token Index: 391

Text #18

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0235. Min Act: -0.0002

Data Index: 1605704 (Python Code)

Max Activating Token Index: 113

Text #19

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0225. Min Act: -0.0002

Data Index: 126902 (C4 (Web Text))

Max Activating Token Index: 816