Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 417 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4164. Min Range: -0.4164

Max Act: 0.4164. Min Act: -0.0002

Data Index: 824136 (C4 (Web Text))

Max Activating Token Index: 478

Text #1

Max Range: 0.4164. Min Range: -0.4164

Max Act: 0.3782. Min Act: -0.0003

Data Index: 498780 (C4 (Web Text))

Max Activating Token Index: 197

Text #2

Max Range: 0.4164. Min Range: -0.4164

Max Act: 0.3400. Min Act: -0.0002

Data Index: 804340 (C4 (Web Text))

Max Activating Token Index: 429

Text #3

Max Range: 0.4164. Min Range: -0.4164

Max Act: 0.3145. Min Act: -0.0002

Data Index: 766317 (C4 (Web Text))

Max Activating Token Index: 203

Text #4

Max Range: 0.4164. Min Range: -0.4164

Max Act: 0.3234. Min Act: -0.0002

Data Index: 582747 (C4 (Web Text))

Max Activating Token Index: 975

Text #5

Max Range: 0.4164. Min Range: -0.4164

Max Act: 0.3061. Min Act: -0.0002

Data Index: 1092435 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 0.4164. Min Range: -0.4164

Max Act: 0.3003. Min Act: -0.0002

Data Index: 990604 (C4 (Web Text))

Max Activating Token Index: 545

Text #7

Max Range: 0.4164. Min Range: -0.4164

Max Act: 0.2878. Min Act: -0.0002

Data Index: 502892 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 0.4164. Min Range: -0.4164

Max Act: 0.2852. Min Act: -0.0002

Data Index: 430006 (C4 (Web Text))

Max Activating Token Index: 655

Text #9

Max Range: 0.4164. Min Range: -0.4164

Max Act: 0.2816. Min Act: -0.0003

Data Index: 247039 (C4 (Web Text))

Max Activating Token Index: 173

Text #10

Max Range: 0.4164. Min Range: -0.4164

Max Act: 0.2815. Min Act: -0.0002

Data Index: 782692 (C4 (Web Text))

Max Activating Token Index: 238

Text #11

Max Range: 0.4164. Min Range: -0.4164

Max Act: 0.2911. Min Act: -0.0003

Data Index: 493247 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 0.4164. Min Range: -0.4164

Max Act: 0.2755. Min Act: -0.0002

Data Index: 578484 (C4 (Web Text))

Max Activating Token Index: 944

Text #13

Max Range: 0.4164. Min Range: -0.4164

Max Act: 0.2757. Min Act: -0.0003

Data Index: 152150 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 0.4164. Min Range: -0.4164

Max Act: 0.2733. Min Act: -0.0002

Data Index: 1314066 (C4 (Web Text))

Max Activating Token Index: 729

Text #15

Max Range: 0.4164. Min Range: -0.4164

Max Act: 0.2640. Min Act: -0.0003

Data Index: 788971 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 0.4164. Min Range: -0.4164

Max Act: 0.2628. Min Act: -0.0002

Data Index: 870917 (C4 (Web Text))

Max Activating Token Index: 396

Text #17

Max Range: 0.4164. Min Range: -0.4164

Max Act: 0.2604. Min Act: -0.0002

Data Index: 658847 (C4 (Web Text))

Max Activating Token Index: 852

Text #18

Max Range: 0.4164. Min Range: -0.4164

Max Act: 0.2684. Min Act: -0.0002

Data Index: 990393 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 0.4164. Min Range: -0.4164

Max Act: 0.2673. Min Act: -0.0002

Data Index: 495443 (C4 (Web Text))

Max Activating Token Index: 890