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

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

Neuron 1563 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: 0.0331. Min Range: -0.0331

Max Act: 0.0331. Min Act: -0.0002

Data Index: 909177 (C4 (Web Text))

Max Activating Token Index: 379

Text #1

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0315. Min Act: -0.0002

Data Index: 615267 (C4 (Web Text))

Max Activating Token Index: 431

Text #2

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0280. Min Act: -0.0002

Data Index: 1266666 (C4 (Web Text))

Max Activating Token Index: 538

Text #3

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0314. Min Act: -0.0002

Data Index: 99757 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0297. Min Act: -0.0002

Data Index: 926840 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0275. Min Act: -0.0002

Data Index: 1353715 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0245. Min Act: -0.0002

Data Index: 402522 (C4 (Web Text))

Max Activating Token Index: 663

Text #7

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0251. Min Act: -0.0002

Data Index: 1280319 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0225. Min Act: -0.0002

Data Index: 1125011 (C4 (Web Text))

Max Activating Token Index: 222

Text #9

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0264. Min Act: -0.0002

Data Index: 959877 (C4 (Web Text))

Max Activating Token Index: 412

Text #10

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0252. Min Act: -0.0002

Data Index: 162989 (C4 (Web Text))

Max Activating Token Index: 656

Text #11

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0219. Min Act: -0.0002

Data Index: 179240 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0248. Min Act: -0.0002

Data Index: 682059 (C4 (Web Text))

Max Activating Token Index: 426

Text #13

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0232. Min Act: -0.0002

Data Index: 193989 (C4 (Web Text))

Max Activating Token Index: 688

Text #14

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0242. Min Act: -0.0002

Data Index: 725943 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0241. Min Act: -0.0002

Data Index: 140051 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0252. Min Act: -0.0002

Data Index: 446892 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0216. Min Act: -0.0002

Data Index: 751520 (C4 (Web Text))

Max Activating Token Index: 467

Text #18

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0229. Min Act: -0.0002

Data Index: 1588576 (Python Code)

Max Activating Token Index: 339

Text #19

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0214. Min Act: -0.0002

Data Index: 464255 (C4 (Web Text))

Max Activating Token Index: 632