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

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

Neuron 2589 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5867. Min Range: -2.5867

Max Act: 2.5867. Min Act: -0.0000

Data Index: 1360350 (Python Code)

Max Activating Token Index: 138

Text #1

Max Range: 2.5867. Min Range: -2.5867

Max Act: 2.5780. Min Act: -0.0000

Data Index: 352996 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 2.5867. Min Range: -2.5867

Max Act: 2.4793. Min Act: -0.0000

Data Index: 267494 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 2.5867. Min Range: -2.5867

Max Act: 2.0434. Min Act: -0.0000

Data Index: 547984 (C4 (Web Text))

Max Activating Token Index: 513

Text #4

Max Range: 2.5867. Min Range: -2.5867

Max Act: 2.1494. Min Act: -0.0000

Data Index: 1241412 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 2.5867. Min Range: -2.5867

Max Act: 2.2379. Min Act: -0.0000

Data Index: 404689 (C4 (Web Text))

Max Activating Token Index: 367

Text #6

Max Range: 2.5867. Min Range: -2.5867

Max Act: 1.8431. Min Act: -0.0000

Data Index: 1158796 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 2.5867. Min Range: -2.5867

Max Act: 2.0294. Min Act: -0.0000

Data Index: 298952 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 2.5867. Min Range: -2.5867

Max Act: 2.0323. Min Act: -0.0000

Data Index: 1354353 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 2.5867. Min Range: -2.5867

Max Act: 2.1240. Min Act: -0.0000

Data Index: 759936 (C4 (Web Text))

Max Activating Token Index: 605

Text #10

Max Range: 2.5867. Min Range: -2.5867

Max Act: 1.9854. Min Act: -0.0000

Data Index: 263602 (C4 (Web Text))

Max Activating Token Index: 291

Text #11

Max Range: 2.5867. Min Range: -2.5867

Max Act: 1.8669. Min Act: -0.0000

Data Index: 1204291 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 2.5867. Min Range: -2.5867

Max Act: 1.9720. Min Act: -0.0000

Data Index: 257390 (C4 (Web Text))

Max Activating Token Index: 518

Text #13

Max Range: 2.5867. Min Range: -2.5867

Max Act: 1.8616. Min Act: -0.0000

Data Index: 912890 (C4 (Web Text))

Max Activating Token Index: 585

Text #14

Max Range: 2.5867. Min Range: -2.5867

Max Act: 1.8530. Min Act: -0.0000

Data Index: 936727 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 2.5867. Min Range: -2.5867

Max Act: 1.8444. Min Act: -0.0000

Data Index: 831356 (C4 (Web Text))

Max Activating Token Index: 779

Text #16

Max Range: 2.5867. Min Range: -2.5867

Max Act: 1.9054. Min Act: -0.0000

Data Index: 1083592 (C4 (Web Text))

Max Activating Token Index: 923

Text #17

Max Range: 2.5867. Min Range: -2.5867

Max Act: 1.8821. Min Act: -0.0000

Data Index: 990531 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 2.5867. Min Range: -2.5867

Max Act: 1.8878. Min Act: -0.0000

Data Index: 1322371 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 2.5867. Min Range: -2.5867

Max Act: 1.6889. Min Act: -0.0000

Data Index: 377868 (C4 (Web Text))

Max Activating Token Index: 190