Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5941 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.6628. Min Range: -2.6628

Max Act: 2.5392. Min Act: -0.0000

Data Index: 378344 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 2.6628. Min Range: -2.6628

Max Act: 2.6628. Min Act: -0.0000

Data Index: 34984 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 2.6628. Min Range: -2.6628

Max Act: 2.5028. Min Act: -0.0000

Data Index: 1037945 (C4 (Web Text))

Max Activating Token Index: 160

Text #3

Max Range: 2.6628. Min Range: -2.6628

Max Act: 2.4764. Min Act: -0.0000

Data Index: 758940 (C4 (Web Text))

Max Activating Token Index: 175

Text #4

Max Range: 2.6628. Min Range: -2.6628

Max Act: 2.4520. Min Act: -0.0000

Data Index: 1567462 (Python Code)

Max Activating Token Index: 467

Text #5

Max Range: 2.6628. Min Range: -2.6628

Max Act: 2.2288. Min Act: -0.0000

Data Index: 672282 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 2.6628. Min Range: -2.6628

Max Act: 2.3613. Min Act: -0.0000

Data Index: 333483 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 2.6628. Min Range: -2.6628

Max Act: 2.2276. Min Act: -0.0000

Data Index: 318646 (C4 (Web Text))

Max Activating Token Index: 292

Text #8

Max Range: 2.6628. Min Range: -2.6628

Max Act: 2.2253. Min Act: -0.0000

Data Index: 637506 (C4 (Web Text))

Max Activating Token Index: 880

Text #9

Max Range: 2.6628. Min Range: -2.6628

Max Act: 2.1649. Min Act: -0.0000

Data Index: 171953 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 2.6628. Min Range: -2.6628

Max Act: 2.1481. Min Act: -0.0000

Data Index: 1016395 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 2.6628. Min Range: -2.6628

Max Act: 2.2408. Min Act: -0.0000

Data Index: 743265 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 2.6628. Min Range: -2.6628

Max Act: 2.1390. Min Act: -0.0000

Data Index: 961105 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 2.6628. Min Range: -2.6628

Max Act: 2.1033. Min Act: -0.0000

Data Index: 424544 (C4 (Web Text))

Max Activating Token Index: 496

Text #14

Max Range: 2.6628. Min Range: -2.6628

Max Act: 2.0947. Min Act: -0.0000

Data Index: 715478 (C4 (Web Text))

Max Activating Token Index: 539

Text #15

Max Range: 2.6628. Min Range: -2.6628

Max Act: 1.9756. Min Act: -0.0000

Data Index: 944110 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 2.6628. Min Range: -2.6628

Max Act: 1.9689. Min Act: -0.0000

Data Index: 154637 (C4 (Web Text))

Max Activating Token Index: 907

Text #17

Max Range: 2.6628. Min Range: -2.6628

Max Act: 2.0844. Min Act: -0.0000

Data Index: 1265632 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 2.6628. Min Range: -2.6628

Max Act: 2.0629. Min Act: -0.0000

Data Index: 538224 (C4 (Web Text))

Max Activating Token Index: 415

Text #19

Max Range: 2.6628. Min Range: -2.6628

Max Act: 2.0663. Min Act: -0.0000

Data Index: 963896 (C4 (Web Text))

Max Activating Token Index: 900