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

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

Neuron 4680 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: 0.0217. Min Range: -0.0217

Max Act: 0.0217. Min Act: -0.0003

Data Index: 111086 (C4 (Web Text))

Max Activating Token Index: 83

Text #1

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0211. Min Act: -0.0003

Data Index: 1100172 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0201. Min Act: -0.0003

Data Index: 425679 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0197. Min Act: -0.0003

Data Index: 1135416 (C4 (Web Text))

Max Activating Token Index: 680

Text #4

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0197. Min Act: -0.0003

Data Index: 1072230 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0193. Min Act: -0.0003

Data Index: 298683 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0194. Min Act: -0.0003

Data Index: 1272703 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0197. Min Act: -0.0003

Data Index: 1101414 (C4 (Web Text))

Max Activating Token Index: 287

Text #8

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0193. Min Act: -0.0003

Data Index: 219603 (C4 (Web Text))

Max Activating Token Index: 416

Text #9

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0193. Min Act: -0.0003

Data Index: 284895 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0189. Min Act: -0.0003

Data Index: 138564 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0195. Min Act: -0.0003

Data Index: 772451 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0184. Min Act: -0.0003

Data Index: 926087 (C4 (Web Text))

Max Activating Token Index: 805

Text #13

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0189. Min Act: -0.0003

Data Index: 952050 (C4 (Web Text))

Max Activating Token Index: 815

Text #14

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0188. Min Act: -0.0003

Data Index: 1263533 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0192. Min Act: -0.0002

Data Index: 1104413 (C4 (Web Text))

Max Activating Token Index: 996

Text #16

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0182. Min Act: -0.0003

Data Index: 949475 (C4 (Web Text))

Max Activating Token Index: 1017

Text #17

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0190. Min Act: -0.0002

Data Index: 1281425 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0184. Min Act: -0.0003

Data Index: 1311105 (C4 (Web Text))

Max Activating Token Index: 205

Text #19

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0188. Min Act: -0.0003

Data Index: 912610 (C4 (Web Text))

Max Activating Token Index: 481