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

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

Neuron 4634 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.4134. Min Act: -0.0000

Data Index: 792184 (C4 (Web Text))

Max Activating Token Index: 545

Text #1

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.4179. Min Act: 0.0000

Data Index: 886616 (C4 (Web Text))

Max Activating Token Index: 562

Text #2

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.3809. Min Act: -0.0000

Data Index: 1023431 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.3704. Min Act: -0.0000

Data Index: 566345 (C4 (Web Text))

Max Activating Token Index: 1002

Text #4

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.3807. Min Act: -0.0000

Data Index: 1241671 (C4 (Web Text))

Max Activating Token Index: 869

Text #5

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.3815. Min Act: 0.0003

Data Index: 945880 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.3784. Min Act: -0.0000

Data Index: 331244 (C4 (Web Text))

Max Activating Token Index: 367

Text #7

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.3653. Min Act: -0.0000

Data Index: 72888 (C4 (Web Text))

Max Activating Token Index: 663

Text #8

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.3647. Min Act: 0.0001

Data Index: 676060 (C4 (Web Text))

Max Activating Token Index: 690

Text #9

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.3523. Min Act: -0.0000

Data Index: 1240886 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.3464. Min Act: 0.0000

Data Index: 737798 (C4 (Web Text))

Max Activating Token Index: 286

Text #11

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.3585. Min Act: -0.0000

Data Index: 293365 (C4 (Web Text))

Max Activating Token Index: 983

Text #12

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.3289. Min Act: -0.0000

Data Index: 469501 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.3392. Min Act: -0.0000

Data Index: 245669 (C4 (Web Text))

Max Activating Token Index: 925

Text #14

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.3262. Min Act: -0.0000

Data Index: 461837 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.3488. Min Act: -0.0000

Data Index: 728930 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.3356. Min Act: -0.0000

Data Index: 331835 (C4 (Web Text))

Max Activating Token Index: 732

Text #17

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.3409. Min Act: 0.0000

Data Index: 1313847 (C4 (Web Text))

Max Activating Token Index: 206

Text #18

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.3283. Min Act: -0.0000

Data Index: 116511 (C4 (Web Text))

Max Activating Token Index: 160

Text #19

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.3275. Min Act: -0.0000

Data Index: 471334 (C4 (Web Text))

Max Activating Token Index: 921