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

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

Neuron 4516 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.8223. Min Act: -0.0000

Data Index: 885435 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.8479. Min Act: -0.0000

Data Index: 748084 (C4 (Web Text))

Max Activating Token Index: 309

Text #2

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.6596. Min Act: -0.0000

Data Index: 123774 (C4 (Web Text))

Max Activating Token Index: 271

Text #3

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.7318. Min Act: -0.0000

Data Index: 891735 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.6302. Min Act: -0.0000

Data Index: 78297 (C4 (Web Text))

Max Activating Token Index: 940

Text #5

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.6155. Min Act: -0.0000

Data Index: 395751 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.5875. Min Act: -0.0000

Data Index: 1053934 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.5899. Min Act: -0.0000

Data Index: 70238 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.5786. Min Act: -0.0000

Data Index: 479486 (C4 (Web Text))

Max Activating Token Index: 137

Text #9

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.6380. Min Act: -0.0000

Data Index: 1254636 (C4 (Web Text))

Max Activating Token Index: 561

Text #10

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.5235. Min Act: -0.0000

Data Index: 277212 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.5134. Min Act: -0.0000

Data Index: 483471 (C4 (Web Text))

Max Activating Token Index: 911

Text #12

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.5102. Min Act: -0.0000

Data Index: 637139 (C4 (Web Text))

Max Activating Token Index: 151

Text #13

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.4847. Min Act: -0.0000

Data Index: 222017 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.5687. Min Act: -0.0000

Data Index: 596220 (C4 (Web Text))

Max Activating Token Index: 11

Text #15

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.5128. Min Act: -0.0000

Data Index: 875854 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.4197. Min Act: -0.0000

Data Index: 902227 (C4 (Web Text))

Max Activating Token Index: 728

Text #17

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.6310. Min Act: -0.0000

Data Index: 1358247 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.4807. Min Act: -0.0000

Data Index: 883107 (C4 (Web Text))

Max Activating Token Index: 562

Text #19

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.5131. Min Act: -0.0000

Data Index: 686805 (C4 (Web Text))

Max Activating Token Index: 878