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

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

Neuron 4221 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2027. Min Range: -4.2027

Max Act: 4.0401. Min Act: -0.0000

Data Index: 132882 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 4.2027. Min Range: -4.2027

Max Act: 4.2027. Min Act: -0.0000

Data Index: 1160311 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 4.2027. Min Range: -4.2027

Max Act: 3.9817. Min Act: -0.0000

Data Index: 700035 (C4 (Web Text))

Max Activating Token Index: 534

Text #3

Max Range: 4.2027. Min Range: -4.2027

Max Act: 4.0884. Min Act: -0.0000

Data Index: 1020824 (C4 (Web Text))

Max Activating Token Index: 890

Text #4

Max Range: 4.2027. Min Range: -4.2027

Max Act: 4.0456. Min Act: -0.0000

Data Index: 718910 (C4 (Web Text))

Max Activating Token Index: 206

Text #5

Max Range: 4.2027. Min Range: -4.2027

Max Act: 3.9826. Min Act: -0.0000

Data Index: 795674 (C4 (Web Text))

Max Activating Token Index: 476

Text #6

Max Range: 4.2027. Min Range: -4.2027

Max Act: 3.9766. Min Act: -0.0000

Data Index: 1179377 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 4.2027. Min Range: -4.2027

Max Act: 3.9211. Min Act: -0.0000

Data Index: 1262660 (C4 (Web Text))

Max Activating Token Index: 409

Text #8

Max Range: 4.2027. Min Range: -4.2027

Max Act: 3.9258. Min Act: -0.0000

Data Index: 799706 (C4 (Web Text))

Max Activating Token Index: 996

Text #9

Max Range: 4.2027. Min Range: -4.2027

Max Act: 3.4671. Min Act: -0.0000

Data Index: 529806 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 4.2027. Min Range: -4.2027

Max Act: 3.5695. Min Act: -0.0000

Data Index: 381810 (C4 (Web Text))

Max Activating Token Index: 983

Text #11

Max Range: 4.2027. Min Range: -4.2027

Max Act: 3.3854. Min Act: -0.0000

Data Index: 356975 (C4 (Web Text))

Max Activating Token Index: 729

Text #12

Max Range: 4.2027. Min Range: -4.2027

Max Act: 3.0771. Min Act: -0.0000

Data Index: 846162 (C4 (Web Text))

Max Activating Token Index: 28

Text #13

Max Range: 4.2027. Min Range: -4.2027

Max Act: 2.7938. Min Act: -0.0000

Data Index: 519999 (C4 (Web Text))

Max Activating Token Index: 788

Text #14

Max Range: 4.2027. Min Range: -4.2027

Max Act: 3.1490. Min Act: -0.0000

Data Index: 782587 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 4.2027. Min Range: -4.2027

Max Act: 2.6859. Min Act: -0.0000

Data Index: 128545 (C4 (Web Text))

Max Activating Token Index: 703

Text #16

Max Range: 4.2027. Min Range: -4.2027

Max Act: 2.7909. Min Act: -0.0000

Data Index: 74559 (C4 (Web Text))

Max Activating Token Index: 980

Text #17

Max Range: 4.2027. Min Range: -4.2027

Max Act: 2.7790. Min Act: -0.0000

Data Index: 298993 (C4 (Web Text))

Max Activating Token Index: 653

Text #18

Max Range: 4.2027. Min Range: -4.2027

Max Act: 2.7568. Min Act: -0.0000

Data Index: 544605 (C4 (Web Text))

Max Activating Token Index: 965

Text #19

Max Range: 4.2027. Min Range: -4.2027

Max Act: 2.7291. Min Act: -0.0000

Data Index: 1121870 (C4 (Web Text))

Max Activating Token Index: 375