Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3272 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6906. Min Range: -0.6906

Max Act: 0.6906. Min Act: -0.0001

Data Index: 1325811 (C4 (Web Text))

Max Activating Token Index: 497

Text #1

Max Range: 0.6906. Min Range: -0.6906

Max Act: 0.6567. Min Act: -0.0000

Data Index: 572489 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 0.6906. Min Range: -0.6906

Max Act: 0.6586. Min Act: -0.0000

Data Index: 930281 (C4 (Web Text))

Max Activating Token Index: 397

Text #3

Max Range: 0.6906. Min Range: -0.6906

Max Act: 0.6580. Min Act: -0.0001

Data Index: 754445 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 0.6906. Min Range: -0.6906

Max Act: 0.6223. Min Act: -0.0000

Data Index: 270487 (C4 (Web Text))

Max Activating Token Index: 994

Text #5

Max Range: 0.6906. Min Range: -0.6906

Max Act: 0.6152. Min Act: -0.0001

Data Index: 906833 (C4 (Web Text))

Max Activating Token Index: 188

Text #6

Max Range: 0.6906. Min Range: -0.6906

Max Act: 0.5912. Min Act: -0.0001

Data Index: 220472 (C4 (Web Text))

Max Activating Token Index: 347

Text #7

Max Range: 0.6906. Min Range: -0.6906

Max Act: 0.5870. Min Act: -0.0000

Data Index: 795771 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 0.6906. Min Range: -0.6906

Max Act: 0.5491. Min Act: -0.0001

Data Index: 572074 (C4 (Web Text))

Max Activating Token Index: 173

Text #9

Max Range: 0.6906. Min Range: -0.6906

Max Act: 0.5522. Min Act: -0.0000

Data Index: 270732 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 0.6906. Min Range: -0.6906

Max Act: 0.5496. Min Act: -0.0000

Data Index: 258147 (C4 (Web Text))

Max Activating Token Index: 565

Text #11

Max Range: 0.6906. Min Range: -0.6906

Max Act: 0.5405. Min Act: -0.0000

Data Index: 1104895 (C4 (Web Text))

Max Activating Token Index: 484

Text #12

Max Range: 0.6906. Min Range: -0.6906

Max Act: 0.5224. Min Act: -0.0000

Data Index: 449846 (C4 (Web Text))

Max Activating Token Index: 700

Text #13

Max Range: 0.6906. Min Range: -0.6906

Max Act: 0.5209. Min Act: -0.0001

Data Index: 1002340 (C4 (Web Text))

Max Activating Token Index: 803

Text #14

Max Range: 0.6906. Min Range: -0.6906

Max Act: 0.5383. Min Act: -0.0000

Data Index: 172021 (C4 (Web Text))

Max Activating Token Index: 983

Text #15

Max Range: 0.6906. Min Range: -0.6906

Max Act: 0.5196. Min Act: -0.0000

Data Index: 903899 (C4 (Web Text))

Max Activating Token Index: 319

Text #16

Max Range: 0.6906. Min Range: -0.6906

Max Act: 0.5392. Min Act: -0.0000

Data Index: 517331 (C4 (Web Text))

Max Activating Token Index: 1012

Text #17

Max Range: 0.6906. Min Range: -0.6906

Max Act: 0.5210. Min Act: -0.0001

Data Index: 49752 (C4 (Web Text))

Max Activating Token Index: 800

Text #18

Max Range: 0.6906. Min Range: -0.6906

Max Act: 0.5198. Min Act: -0.0000

Data Index: 885525 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 0.6906. Min Range: -0.6906

Max Act: 0.5024. Min Act: -0.0000

Data Index: 1324782 (C4 (Web Text))

Max Activating Token Index: 665