Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 653 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0314. Min Act: -0.0006

Data Index: 372805 (C4 (Web Text))

Max Activating Token Index: 566

Text #1

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0309. Min Act: -0.0006

Data Index: 1283166 (C4 (Web Text))

Max Activating Token Index: 522

Text #2

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0284. Min Act: -0.0006

Data Index: 817966 (C4 (Web Text))

Max Activating Token Index: 289

Text #3

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0271. Min Act: -0.0006

Data Index: 170230 (C4 (Web Text))

Max Activating Token Index: 638

Text #4

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0260. Min Act: -0.0006

Data Index: 260178 (C4 (Web Text))

Max Activating Token Index: 804

Text #5

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0257. Min Act: -0.0006

Data Index: 271150 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0283. Min Act: -0.0006

Data Index: 484467 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0284. Min Act: -0.0006

Data Index: 1179343 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0283. Min Act: -0.0006

Data Index: 569337 (C4 (Web Text))

Max Activating Token Index: 658

Text #9

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0288. Min Act: -0.0006

Data Index: 1133379 (C4 (Web Text))

Max Activating Token Index: 398

Text #10

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0276. Min Act: -0.0006

Data Index: 216282 (C4 (Web Text))

Max Activating Token Index: 738

Text #11

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0246. Min Act: -0.0006

Data Index: 203853 (C4 (Web Text))

Max Activating Token Index: 454

Text #12

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0273. Min Act: -0.0006

Data Index: 1117858 (C4 (Web Text))

Max Activating Token Index: 610

Text #13

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0260. Min Act: -0.0006

Data Index: 1318039 (C4 (Web Text))

Max Activating Token Index: 691

Text #14

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0267. Min Act: -0.0006

Data Index: 981445 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0259. Min Act: -0.0006

Data Index: 166054 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0252. Min Act: -0.0006

Data Index: 822072 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0267. Min Act: -0.0006

Data Index: 1048699 (C4 (Web Text))

Max Activating Token Index: 676

Text #18

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0249. Min Act: -0.0006

Data Index: 1297098 (C4 (Web Text))

Max Activating Token Index: 404

Text #19

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0228. Min Act: -0.0006

Data Index: 103900 (C4 (Web Text))

Max Activating Token Index: 588