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

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

Neuron 2986 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: 0.0322. Min Range: -0.0322

Max Act: 0.0322. Min Act: -0.0003

Data Index: 138926 (C4 (Web Text))

Max Activating Token Index: 378

Text #1

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0288. Min Act: -0.0002

Data Index: 1407773 (Python Code)

Max Activating Token Index: 423

Text #2

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0271. Min Act: -0.0002

Data Index: 672385 (C4 (Web Text))

Max Activating Token Index: 456

Text #3

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0245. Min Act: -0.0002

Data Index: 1491146 (Python Code)

Max Activating Token Index: 142

Text #4

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0218. Min Act: -0.0002

Data Index: 327459 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0190. Min Act: -0.0002

Data Index: 17041 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0225. Min Act: -0.0002

Data Index: 597933 (C4 (Web Text))

Max Activating Token Index: 236

Text #7

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0194. Min Act: -0.0002

Data Index: 410377 (C4 (Web Text))

Max Activating Token Index: 677

Text #8

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0211. Min Act: -0.0002

Data Index: 1649197 (Python Code)

Max Activating Token Index: 144

Text #9

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0229. Min Act: -0.0002

Data Index: 729824 (C4 (Web Text))

Max Activating Token Index: 819

Text #10

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0218. Min Act: -0.0002

Data Index: 304367 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0230. Min Act: -0.0002

Data Index: 1368361 (Python Code)

Max Activating Token Index: 173

Text #12

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0224. Min Act: -0.0002

Data Index: 1531149 (Python Code)

Max Activating Token Index: 939

Text #13

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0233. Min Act: -0.0002

Data Index: 850660 (C4 (Web Text))

Max Activating Token Index: 710

Text #14

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0218. Min Act: -0.0002

Data Index: 846902 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0214. Min Act: -0.0002

Data Index: 762910 (C4 (Web Text))

Max Activating Token Index: 911

Text #16

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0208. Min Act: -0.0002

Data Index: 1218409 (C4 (Web Text))

Max Activating Token Index: 155

Text #17

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0229. Min Act: -0.0002

Data Index: 157571 (C4 (Web Text))

Max Activating Token Index: 259

Text #18

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0215. Min Act: -0.0002

Data Index: 678584 (C4 (Web Text))

Max Activating Token Index: 560

Text #19

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0213. Min Act: -0.0003

Data Index: 44399 (C4 (Web Text))

Max Activating Token Index: 794