Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3368 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0310. Min Act: -0.0003

Data Index: 1223394 (C4 (Web Text))

Max Activating Token Index: 481

Text #1

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0309. Min Act: -0.0003

Data Index: 832911 (C4 (Web Text))

Max Activating Token Index: 463

Text #2

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0294. Min Act: -0.0003

Data Index: 1140445 (C4 (Web Text))

Max Activating Token Index: 787

Text #3

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0275. Min Act: -0.0003

Data Index: 428943 (C4 (Web Text))

Max Activating Token Index: 341

Text #4

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0294. Min Act: -0.0003

Data Index: 397866 (C4 (Web Text))

Max Activating Token Index: 622

Text #5

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0282. Min Act: -0.0003

Data Index: 1240641 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0257. Min Act: -0.0003

Data Index: 1141022 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0273. Min Act: -0.0003

Data Index: 664589 (C4 (Web Text))

Max Activating Token Index: 731

Text #8

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0247. Min Act: -0.0003

Data Index: 219311 (C4 (Web Text))

Max Activating Token Index: 392

Text #9

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0246. Min Act: -0.0003

Data Index: 638351 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0233. Min Act: -0.0003

Data Index: 857564 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0237. Min Act: -0.0003

Data Index: 868445 (C4 (Web Text))

Max Activating Token Index: 323

Text #12

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0236. Min Act: -0.0003

Data Index: 773342 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0242. Min Act: -0.0003

Data Index: 1579179 (Python Code)

Max Activating Token Index: 460

Text #14

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0223. Min Act: -0.0003

Data Index: 988390 (C4 (Web Text))

Max Activating Token Index: 940

Text #15

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0227. Min Act: -0.0003

Data Index: 593612 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0222. Min Act: -0.0003

Data Index: 993641 (C4 (Web Text))

Max Activating Token Index: 2

Text #17

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0220. Min Act: -0.0004

Data Index: 1105964 (C4 (Web Text))

Max Activating Token Index: 241

Text #18

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0225. Min Act: -0.0003

Data Index: 1095553 (C4 (Web Text))

Max Activating Token Index: 441

Text #19

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0217. Min Act: -0.0004

Data Index: 57942 (C4 (Web Text))

Max Activating Token Index: 372