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

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

Neuron 2470 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5036. Min Range: -0.5036

Max Act: 0.5036. Min Act: -0.0000

Data Index: 342798 (C4 (Web Text))

Max Activating Token Index: 739

Text #1

Max Range: 0.5036. Min Range: -0.5036

Max Act: 0.5005. Min Act: -0.0000

Data Index: 864756 (C4 (Web Text))

Max Activating Token Index: 180

Text #2

Max Range: 0.5036. Min Range: -0.5036

Max Act: 0.4909. Min Act: -0.0000

Data Index: 583037 (C4 (Web Text))

Max Activating Token Index: 649

Text #3

Max Range: 0.5036. Min Range: -0.5036

Max Act: 0.4721. Min Act: -0.0000

Data Index: 112785 (C4 (Web Text))

Max Activating Token Index: 977

Text #4

Max Range: 0.5036. Min Range: -0.5036

Max Act: 0.4645. Min Act: -0.0000

Data Index: 98240 (C4 (Web Text))

Max Activating Token Index: 824

Text #5

Max Range: 0.5036. Min Range: -0.5036

Max Act: 0.4259. Min Act: -0.0000

Data Index: 128739 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 0.5036. Min Range: -0.5036

Max Act: 0.4473. Min Act: -0.0000

Data Index: 494776 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 0.5036. Min Range: -0.5036

Max Act: 0.4266. Min Act: -0.0000

Data Index: 1090131 (C4 (Web Text))

Max Activating Token Index: 605

Text #8

Max Range: 0.5036. Min Range: -0.5036

Max Act: 0.4228. Min Act: -0.0000

Data Index: 964080 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 0.5036. Min Range: -0.5036

Max Act: 0.4368. Min Act: -0.0000

Data Index: 516962 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 0.5036. Min Range: -0.5036

Max Act: 0.4372. Min Act: -0.0000

Data Index: 910225 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 0.5036. Min Range: -0.5036

Max Act: 0.4289. Min Act: -0.0000

Data Index: 960953 (C4 (Web Text))

Max Activating Token Index: 972

Text #12

Max Range: 0.5036. Min Range: -0.5036

Max Act: 0.4268. Min Act: -0.0000

Data Index: 1071562 (C4 (Web Text))

Max Activating Token Index: 288

Text #13

Max Range: 0.5036. Min Range: -0.5036

Max Act: 0.4400. Min Act: -0.0000

Data Index: 967637 (C4 (Web Text))

Max Activating Token Index: 988

Text #14

Max Range: 0.5036. Min Range: -0.5036

Max Act: 0.4119. Min Act: -0.0000

Data Index: 470230 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 0.5036. Min Range: -0.5036

Max Act: 0.4084. Min Act: -0.0000

Data Index: 625835 (C4 (Web Text))

Max Activating Token Index: 992

Text #16

Max Range: 0.5036. Min Range: -0.5036

Max Act: 0.4220. Min Act: -0.0000

Data Index: 593200 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 0.5036. Min Range: -0.5036

Max Act: 0.4227. Min Act: -0.0000

Data Index: 188910 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 0.5036. Min Range: -0.5036

Max Act: 0.4070. Min Act: -0.0000

Data Index: 953527 (C4 (Web Text))

Max Activating Token Index: 814

Text #19

Max Range: 0.5036. Min Range: -0.5036

Max Act: 0.4152. Min Act: -0.0000

Data Index: 1352402 (C4 (Web Text))

Max Activating Token Index: 84