Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 450 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0205. Min Act: -0.0006

Data Index: 8168 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0207. Min Act: -0.0006

Data Index: 528633 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0199. Min Act: -0.0006

Data Index: 803866 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0207. Min Act: -0.0006

Data Index: 90385 (C4 (Web Text))

Max Activating Token Index: 748

Text #4

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0191. Min Act: -0.0006

Data Index: 814466 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0198. Min Act: -0.0006

Data Index: 339088 (C4 (Web Text))

Max Activating Token Index: 193

Text #6

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0194. Min Act: -0.0006

Data Index: 1137845 (C4 (Web Text))

Max Activating Token Index: 890

Text #7

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0194. Min Act: -0.0006

Data Index: 489405 (C4 (Web Text))

Max Activating Token Index: 378

Text #8

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0192. Min Act: -0.0006

Data Index: 1350579 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0189. Min Act: -0.0006

Data Index: 766956 (C4 (Web Text))

Max Activating Token Index: 721

Text #10

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0197. Min Act: -0.0006

Data Index: 1217088 (C4 (Web Text))

Max Activating Token Index: 333

Text #11

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0188. Min Act: -0.0006

Data Index: 32044 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0179. Min Act: -0.0006

Data Index: 1087123 (C4 (Web Text))

Max Activating Token Index: 696

Text #13

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0195. Min Act: -0.0006

Data Index: 280246 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0199. Min Act: -0.0006

Data Index: 86175 (C4 (Web Text))

Max Activating Token Index: 469

Text #15

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0193. Min Act: -0.0006

Data Index: 120493 (C4 (Web Text))

Max Activating Token Index: 634

Text #16

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0177. Min Act: -0.0006

Data Index: 858743 (C4 (Web Text))

Max Activating Token Index: 810

Text #17

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0178. Min Act: -0.0006

Data Index: 161500 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0194. Min Act: -0.0006

Data Index: 1217849 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0193. Min Act: -0.0006

Data Index: 1299610 (C4 (Web Text))

Max Activating Token Index: 622