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

Dataset: The Pile

Neuron 1236 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.8264. Min Act: -0.0000

Data Index: 612275 (The Pile)

Max Activating Token Index: 42

Text #1

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.7856. Min Act: -0.0000

Data Index: 401682 (The Pile)

Max Activating Token Index: 599

Text #2

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.7512. Min Act: -0.0000

Data Index: 304609 (The Pile)

Max Activating Token Index: 339

Text #3

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.6851. Min Act: -0.0000

Data Index: 652419 (The Pile)

Max Activating Token Index: 181

Text #4

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.7733. Min Act: -0.0000

Data Index: 1560794 (The Pile)

Max Activating Token Index: 861

Text #5

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.7006. Min Act: -0.0000

Data Index: 1616013 (The Pile)

Max Activating Token Index: 66

Text #6

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.5933. Min Act: -0.0000

Data Index: 1711339 (The Pile)

Max Activating Token Index: 55

Text #7

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.7008. Min Act: -0.0000

Data Index: 820714 (The Pile)

Max Activating Token Index: 701

Text #8

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.6768. Min Act: -0.0000

Data Index: 978356 (The Pile)

Max Activating Token Index: 506

Text #9

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.6401. Min Act: -0.0000

Data Index: 1981161 (The Pile)

Max Activating Token Index: 688

Text #10

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.7310. Min Act: -0.0000

Data Index: 1336445 (The Pile)

Max Activating Token Index: 709

Text #11

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.5725. Min Act: -0.0000

Data Index: 1878153 (The Pile)

Max Activating Token Index: 792

Text #12

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.5607. Min Act: -0.0000

Data Index: 1917451 (The Pile)

Max Activating Token Index: 748

Text #13

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.5885. Min Act: -0.0000

Data Index: 89496 (The Pile)

Max Activating Token Index: 597

Text #14

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.6095. Min Act: -0.0000

Data Index: 1502646 (The Pile)

Max Activating Token Index: 83

Text #15

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.6811. Min Act: -0.0000

Data Index: 1033527 (The Pile)

Max Activating Token Index: 202

Text #16

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.6382. Min Act: -0.0000

Data Index: 18256 (The Pile)

Max Activating Token Index: 668

Text #17

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.6296. Min Act: -0.0000

Data Index: 509157 (The Pile)

Max Activating Token Index: 343

Text #18

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.5893. Min Act: -0.0000

Data Index: 214124 (The Pile)

Max Activating Token Index: 604

Text #19

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.6041. Min Act: -0.0000

Data Index: 1055855 (The Pile)

Max Activating Token Index: 172