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

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

Neuron 4092 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0264. Min Act: -0.0002

Data Index: 884448 (C4 (Web Text))

Max Activating Token Index: 276

Text #1

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0252. Min Act: -0.0003

Data Index: 375147 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0240. Min Act: -0.0002

Data Index: 888964 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0240. Min Act: -0.0003

Data Index: 352772 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0229. Min Act: -0.0003

Data Index: 432550 (C4 (Web Text))

Max Activating Token Index: 225

Text #5

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0224. Min Act: -0.0002

Data Index: 35590 (C4 (Web Text))

Max Activating Token Index: 547

Text #6

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0219. Min Act: -0.0002

Data Index: 1530651 (Python Code)

Max Activating Token Index: 882

Text #7

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0209. Min Act: -0.0003

Data Index: 666409 (C4 (Web Text))

Max Activating Token Index: 394

Text #8

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0211. Min Act: -0.0003

Data Index: 408085 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0206. Min Act: -0.0002

Data Index: 510640 (C4 (Web Text))

Max Activating Token Index: 344

Text #10

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0212. Min Act: -0.0003

Data Index: 886874 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0205. Min Act: -0.0002

Data Index: 691618 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0206. Min Act: -0.0002

Data Index: 665274 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0202. Min Act: -0.0002

Data Index: 1635657 (Python Code)

Max Activating Token Index: 517

Text #14

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0206. Min Act: -0.0002

Data Index: 1428903 (Python Code)

Max Activating Token Index: 305

Text #15

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0205. Min Act: -0.0003

Data Index: 965654 (C4 (Web Text))

Max Activating Token Index: 235

Text #16

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0199. Min Act: -0.0002

Data Index: 1263415 (C4 (Web Text))

Max Activating Token Index: 258

Text #17

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0201. Min Act: -0.0003

Data Index: 327486 (C4 (Web Text))

Max Activating Token Index: 346

Text #18

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0195. Min Act: -0.0002

Data Index: 243775 (C4 (Web Text))

Max Activating Token Index: 284

Text #19

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0202. Min Act: -0.0002

Data Index: 730387 (C4 (Web Text))

Max Activating Token Index: 193