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

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

Neuron 2493 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.7603. Min Act: -0.0000

Data Index: 178277 (C4 (Web Text))

Max Activating Token Index: 789

Text #1

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.7195. Min Act: 0.0000

Data Index: 623993 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.6752. Min Act: -0.0000

Data Index: 1108138 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.6568. Min Act: -0.0000

Data Index: 1126890 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.6686. Min Act: -0.0000

Data Index: 1033705 (C4 (Web Text))

Max Activating Token Index: 230

Text #5

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.6753. Min Act: 0.0000

Data Index: 45797 (C4 (Web Text))

Max Activating Token Index: 191

Text #6

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.6158. Min Act: -0.0000

Data Index: 206293 (C4 (Web Text))

Max Activating Token Index: 359

Text #7

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.6455. Min Act: -0.0000

Data Index: 82197 (C4 (Web Text))

Max Activating Token Index: 748

Text #8

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.6265. Min Act: -0.0000

Data Index: 1314778 (C4 (Web Text))

Max Activating Token Index: 611

Text #9

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.6003. Min Act: -0.0000

Data Index: 338850 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.5561. Min Act: -0.0000

Data Index: 514032 (C4 (Web Text))

Max Activating Token Index: 707

Text #11

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.5362. Min Act: 0.0000

Data Index: 1162776 (C4 (Web Text))

Max Activating Token Index: 719

Text #12

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.5508. Min Act: -0.0000

Data Index: 361779 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.5479. Min Act: -0.0000

Data Index: 1095869 (C4 (Web Text))

Max Activating Token Index: 315

Text #14

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.5346. Min Act: -0.0000

Data Index: 192927 (C4 (Web Text))

Max Activating Token Index: 765

Text #15

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.5150. Min Act: -0.0000

Data Index: 766546 (C4 (Web Text))

Max Activating Token Index: 828

Text #16

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.5377. Min Act: -0.0000

Data Index: 1012648 (C4 (Web Text))

Max Activating Token Index: 768

Text #17

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.5157. Min Act: -0.0000

Data Index: 622514 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.5243. Min Act: -0.0000

Data Index: 675457 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.4892. Min Act: 0.0000

Data Index: 581215 (C4 (Web Text))

Max Activating Token Index: 728