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

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

Neuron 115 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2754. Min Act: -0.0002

Data Index: 422362 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.3066. Min Act: -0.0002

Data Index: 329442 (C4 (Web Text))

Max Activating Token Index: 411

Text #2

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.3096. Min Act: -0.0001

Data Index: 587662 (C4 (Web Text))

Max Activating Token Index: 171

Text #3

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.3097. Min Act: -0.0001

Data Index: 851395 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2611. Min Act: -0.0001

Data Index: 225339 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2658. Min Act: -0.0002

Data Index: 1288081 (C4 (Web Text))

Max Activating Token Index: 976

Text #6

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2583. Min Act: -0.0002

Data Index: 483559 (C4 (Web Text))

Max Activating Token Index: 950

Text #7

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2531. Min Act: -0.0002

Data Index: 171814 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2685. Min Act: -0.0002

Data Index: 669075 (C4 (Web Text))

Max Activating Token Index: 975

Text #9

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2587. Min Act: -0.0001

Data Index: 910665 (C4 (Web Text))

Max Activating Token Index: 918

Text #10

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2516. Min Act: -0.0002

Data Index: 256377 (C4 (Web Text))

Max Activating Token Index: 737

Text #11

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2506. Min Act: -0.0001

Data Index: 811846 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2167. Min Act: -0.0002

Data Index: 169347 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2329. Min Act: -0.0001

Data Index: 184798 (C4 (Web Text))

Max Activating Token Index: 962

Text #14

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2392. Min Act: -0.0001

Data Index: 453901 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2379. Min Act: -0.0002

Data Index: 120214 (C4 (Web Text))

Max Activating Token Index: 911

Text #16

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2266. Min Act: -0.0002

Data Index: 709836 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2343. Min Act: -0.0002

Data Index: 1078672 (C4 (Web Text))

Max Activating Token Index: 462

Text #18

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2415. Min Act: -0.0001

Data Index: 795925 (C4 (Web Text))

Max Activating Token Index: 264

Text #19

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2311. Min Act: -0.0001

Data Index: 1214954 (C4 (Web Text))

Max Activating Token Index: 414