Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 484 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0331. Min Act: -0.0003

Data Index: 408824 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0239. Min Act: -0.0003

Data Index: 503147 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0236. Min Act: -0.0003

Data Index: 1143056 (C4 (Web Text))

Max Activating Token Index: 315

Text #3

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0230. Min Act: -0.0003

Data Index: 1161117 (C4 (Web Text))

Max Activating Token Index: 437

Text #4

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0220. Min Act: -0.0003

Data Index: 382366 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0211. Min Act: -0.0003

Data Index: 388624 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0218. Min Act: -0.0003

Data Index: 1012077 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0208. Min Act: -0.0003

Data Index: 771741 (C4 (Web Text))

Max Activating Token Index: 651

Text #8

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0214. Min Act: -0.0003

Data Index: 1130453 (C4 (Web Text))

Max Activating Token Index: 735

Text #9

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0213. Min Act: -0.0003

Data Index: 1568454 (Python Code)

Max Activating Token Index: 385

Text #10

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0216. Min Act: -0.0003

Data Index: 79934 (C4 (Web Text))

Max Activating Token Index: 720

Text #11

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0206. Min Act: -0.0003

Data Index: 9076 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0208. Min Act: -0.0003

Data Index: 1032377 (C4 (Web Text))

Max Activating Token Index: 409

Text #13

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0200. Min Act: -0.0003

Data Index: 521604 (C4 (Web Text))

Max Activating Token Index: 25

Text #14

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0198. Min Act: -0.0003

Data Index: 494060 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0196. Min Act: -0.0003

Data Index: 1545297 (Python Code)

Max Activating Token Index: 276

Text #16

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0204. Min Act: -0.0002

Data Index: 37097 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0197. Min Act: -0.0003

Data Index: 1184429 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0191. Min Act: -0.0003

Data Index: 474676 (C4 (Web Text))

Max Activating Token Index: 635

Text #19

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0182. Min Act: -0.0004

Data Index: 51804 (C4 (Web Text))

Max Activating Token Index: 809