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

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

Neuron 27 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0233. Min Act: -0.0002

Data Index: 212567 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0225. Min Act: -0.0003

Data Index: 1319511 (C4 (Web Text))

Max Activating Token Index: 308

Text #2

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0221. Min Act: -0.0003

Data Index: 954413 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0210. Min Act: -0.0003

Data Index: 983178 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0199. Min Act: -0.0003

Data Index: 687467 (C4 (Web Text))

Max Activating Token Index: 129

Text #5

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0192. Min Act: -0.0003

Data Index: 693699 (C4 (Web Text))

Max Activating Token Index: 869

Text #6

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0199. Min Act: -0.0003

Data Index: 614848 (C4 (Web Text))

Max Activating Token Index: 579

Text #7

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0195. Min Act: -0.0003

Data Index: 324797 (C4 (Web Text))

Max Activating Token Index: 202

Text #8

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0205. Min Act: -0.0003

Data Index: 424998 (C4 (Web Text))

Max Activating Token Index: 897

Text #9

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0192. Min Act: -0.0003

Data Index: 1132545 (C4 (Web Text))

Max Activating Token Index: 442

Text #10

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0206. Min Act: -0.0003

Data Index: 812205 (C4 (Web Text))

Max Activating Token Index: 725

Text #11

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0212. Min Act: -0.0002

Data Index: 1358060 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0192. Min Act: -0.0003

Data Index: 340337 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0190. Min Act: -0.0003

Data Index: 276034 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0186. Min Act: -0.0003

Data Index: 913976 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0169. Min Act: -0.0003

Data Index: 845100 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0178. Min Act: -0.0003

Data Index: 538650 (C4 (Web Text))

Max Activating Token Index: 610

Text #17

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0181. Min Act: -0.0003

Data Index: 20057 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0177. Min Act: -0.0003

Data Index: 868174 (C4 (Web Text))

Max Activating Token Index: 681

Text #19

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0171. Min Act: -0.0003

Data Index: 591220 (C4 (Web Text))

Max Activating Token Index: 876