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

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

Neuron 383 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0227. Min Act: -0.0006

Data Index: 512420 (C4 (Web Text))

Max Activating Token Index: 537

Text #1

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0202. Min Act: -0.0006

Data Index: 345996 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0195. Min Act: -0.0006

Data Index: 464073 (C4 (Web Text))

Max Activating Token Index: 771

Text #3

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0187. Min Act: -0.0006

Data Index: 456845 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0195. Min Act: -0.0006

Data Index: 256446 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0195. Min Act: -0.0006

Data Index: 368936 (C4 (Web Text))

Max Activating Token Index: 642

Text #6

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0190. Min Act: -0.0006

Data Index: 942091 (C4 (Web Text))

Max Activating Token Index: 548

Text #7

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0195. Min Act: -0.0006

Data Index: 854186 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0199. Min Act: -0.0006

Data Index: 363779 (C4 (Web Text))

Max Activating Token Index: 496

Text #9

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0185. Min Act: -0.0006

Data Index: 1170572 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0180. Min Act: -0.0006

Data Index: 752723 (C4 (Web Text))

Max Activating Token Index: 603

Text #11

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0187. Min Act: -0.0006

Data Index: 1107753 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0182. Min Act: -0.0006

Data Index: 1094408 (C4 (Web Text))

Max Activating Token Index: 55

Text #13

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0185. Min Act: -0.0006

Data Index: 1197664 (C4 (Web Text))

Max Activating Token Index: 144

Text #14

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0183. Min Act: -0.0005

Data Index: 162522 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0179. Min Act: -0.0006

Data Index: 108781 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0178. Min Act: -0.0006

Data Index: 836597 (C4 (Web Text))

Max Activating Token Index: 991

Text #17

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0186. Min Act: -0.0006

Data Index: 814724 (C4 (Web Text))

Max Activating Token Index: 446

Text #18

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0174. Min Act: -0.0006

Data Index: 433773 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0177. Min Act: -0.0006

Data Index: 1166237 (C4 (Web Text))

Max Activating Token Index: 823