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

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

Neuron 1528 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: 0.0216. Min Range: -0.0216

Max Act: 0.0209. Min Act: -0.0006

Data Index: 76566 (C4 (Web Text))

Max Activating Token Index: 509

Text #1

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0211. Min Act: -0.0006

Data Index: 1172897 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0198. Min Act: -0.0006

Data Index: 1295073 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0197. Min Act: -0.0006

Data Index: 443199 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0196. Min Act: -0.0006

Data Index: 584519 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0189. Min Act: -0.0006

Data Index: 186986 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0184. Min Act: -0.0006

Data Index: 41205 (C4 (Web Text))

Max Activating Token Index: 698

Text #7

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0189. Min Act: -0.0006

Data Index: 307474 (C4 (Web Text))

Max Activating Token Index: 653

Text #8

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0198. Min Act: -0.0006

Data Index: 824861 (C4 (Web Text))

Max Activating Token Index: 436

Text #9

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0187. Min Act: -0.0006

Data Index: 39295 (C4 (Web Text))

Max Activating Token Index: 698

Text #10

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0188. Min Act: -0.0006

Data Index: 730172 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0216. Min Act: -0.0006

Data Index: 161843 (C4 (Web Text))

Max Activating Token Index: 819

Text #12

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0163. Min Act: -0.0006

Data Index: 1154150 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0183. Min Act: -0.0006

Data Index: 323738 (C4 (Web Text))

Max Activating Token Index: 482

Text #14

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0187. Min Act: -0.0006

Data Index: 308034 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0191. Min Act: -0.0006

Data Index: 675767 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0191. Min Act: -0.0006

Data Index: 823283 (C4 (Web Text))

Max Activating Token Index: 426

Text #17

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0190. Min Act: -0.0006

Data Index: 1117662 (C4 (Web Text))

Max Activating Token Index: 962

Text #18

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0195. Min Act: -0.0006

Data Index: 616958 (C4 (Web Text))

Max Activating Token Index: 611

Text #19

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0185. Min Act: -0.0006

Data Index: 238258 (C4 (Web Text))

Max Activating Token Index: 590