Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1775 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0198. Min Act: -0.0006

Data Index: 73303 (C4 (Web Text))

Max Activating Token Index: 212

Text #1

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0200. Min Act: -0.0006

Data Index: 762135 (C4 (Web Text))

Max Activating Token Index: 295

Text #2

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0196. Min Act: -0.0006

Data Index: 1352376 (C4 (Web Text))

Max Activating Token Index: 549

Text #3

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0192. Min Act: -0.0006

Data Index: 402908 (C4 (Web Text))

Max Activating Token Index: 801

Text #4

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0190. Min Act: -0.0006

Data Index: 1141939 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0191. Min Act: -0.0006

Data Index: 46584 (C4 (Web Text))

Max Activating Token Index: 911

Text #6

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0188. Min Act: -0.0006

Data Index: 1273304 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0187. Min Act: -0.0006

Data Index: 1053168 (C4 (Web Text))

Max Activating Token Index: 281

Text #8

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0185. Min Act: -0.0006

Data Index: 678213 (C4 (Web Text))

Max Activating Token Index: 709

Text #9

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0189. Min Act: -0.0006

Data Index: 207347 (C4 (Web Text))

Max Activating Token Index: 296

Text #10

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0186. Min Act: -0.0006

Data Index: 165471 (C4 (Web Text))

Max Activating Token Index: 343

Text #11

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0186. Min Act: -0.0006

Data Index: 205181 (C4 (Web Text))

Max Activating Token Index: 246

Text #12

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0182. Min Act: -0.0006

Data Index: 49666 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0183. Min Act: -0.0006

Data Index: 1340633 (C4 (Web Text))

Max Activating Token Index: 656

Text #14

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0181. Min Act: -0.0006

Data Index: 1103428 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0179. Min Act: -0.0006

Data Index: 1282240 (C4 (Web Text))

Max Activating Token Index: 996

Text #16

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0179. Min Act: -0.0006

Data Index: 42512 (C4 (Web Text))

Max Activating Token Index: 498

Text #17

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0181. Min Act: -0.0006

Data Index: 752573 (C4 (Web Text))

Max Activating Token Index: 894

Text #18

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0180. Min Act: -0.0006

Data Index: 542886 (C4 (Web Text))

Max Activating Token Index: 398

Text #19

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0177. Min Act: -0.0006

Data Index: 1105276 (C4 (Web Text))

Max Activating Token Index: 928