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

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

Neuron 4312 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: 1.0178. Min Range: -1.0178

Max Act: 1.0178. Min Act: -0.0001

Data Index: 426728 (C4 (Web Text))

Max Activating Token Index: 1021

Text #1

Max Range: 1.0178. Min Range: -1.0178

Max Act: 0.8511. Min Act: -0.0000

Data Index: 616612 (C4 (Web Text))

Max Activating Token Index: 467

Text #2

Max Range: 1.0178. Min Range: -1.0178

Max Act: 0.8273. Min Act: -0.0000

Data Index: 685195 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 1.0178. Min Range: -1.0178

Max Act: 0.8199. Min Act: -0.0000

Data Index: 1301157 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 1.0178. Min Range: -1.0178

Max Act: 0.8036. Min Act: -0.0000

Data Index: 748146 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 1.0178. Min Range: -1.0178

Max Act: 0.7513. Min Act: -0.0000

Data Index: 89056 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 1.0178. Min Range: -1.0178

Max Act: 0.7148. Min Act: -0.0000

Data Index: 1338659 (C4 (Web Text))

Max Activating Token Index: 449

Text #7

Max Range: 1.0178. Min Range: -1.0178

Max Act: 0.7473. Min Act: -0.0000

Data Index: 667782 (C4 (Web Text))

Max Activating Token Index: 191

Text #8

Max Range: 1.0178. Min Range: -1.0178

Max Act: 0.6305. Min Act: -0.0000

Data Index: 684530 (C4 (Web Text))

Max Activating Token Index: 492

Text #9

Max Range: 1.0178. Min Range: -1.0178

Max Act: 0.7296. Min Act: -0.0000

Data Index: 278019 (C4 (Web Text))

Max Activating Token Index: 400

Text #10

Max Range: 1.0178. Min Range: -1.0178

Max Act: 0.7008. Min Act: -0.0000

Data Index: 383599 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 1.0178. Min Range: -1.0178

Max Act: 0.7439. Min Act: -0.0000

Data Index: 781375 (C4 (Web Text))

Max Activating Token Index: 182

Text #12

Max Range: 1.0178. Min Range: -1.0178

Max Act: 0.7585. Min Act: -0.0000

Data Index: 1027703 (C4 (Web Text))

Max Activating Token Index: 198

Text #13

Max Range: 1.0178. Min Range: -1.0178

Max Act: 0.7139. Min Act: -0.0000

Data Index: 305430 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 1.0178. Min Range: -1.0178

Max Act: 0.7084. Min Act: -0.0000

Data Index: 696409 (C4 (Web Text))

Max Activating Token Index: 168

Text #15

Max Range: 1.0178. Min Range: -1.0178

Max Act: 0.6882. Min Act: -0.0000

Data Index: 437822 (C4 (Web Text))

Max Activating Token Index: 624

Text #16

Max Range: 1.0178. Min Range: -1.0178

Max Act: 0.6982. Min Act: -0.0001

Data Index: 235114 (C4 (Web Text))

Max Activating Token Index: 16

Text #17

Max Range: 1.0178. Min Range: -1.0178

Max Act: 0.6508. Min Act: -0.0000

Data Index: 948334 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 1.0178. Min Range: -1.0178

Max Act: 0.6730. Min Act: -0.0000

Data Index: 1521914 (Python Code)

Max Activating Token Index: 124

Text #19

Max Range: 1.0178. Min Range: -1.0178

Max Act: 0.6813. Min Act: -0.0001

Data Index: 311722 (C4 (Web Text))

Max Activating Token Index: 450