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

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

Neuron 3202 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: 0.8573. Min Range: -0.8573

Max Act: 0.8573. Min Act: -0.0000

Data Index: 429735 (C4 (Web Text))

Max Activating Token Index: 500

Text #1

Max Range: 0.8573. Min Range: -0.8573

Max Act: 0.7611. Min Act: -0.0000

Data Index: 13795 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 0.8573. Min Range: -0.8573

Max Act: 0.7626. Min Act: -0.0000

Data Index: 1042710 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 0.8573. Min Range: -0.8573

Max Act: 0.7621. Min Act: -0.0000

Data Index: 363090 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 0.8573. Min Range: -0.8573

Max Act: 0.6967. Min Act: -0.0000

Data Index: 597791 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 0.8573. Min Range: -0.8573

Max Act: 0.7331. Min Act: -0.0000

Data Index: 3334 (C4 (Web Text))

Max Activating Token Index: 177

Text #6

Max Range: 0.8573. Min Range: -0.8573

Max Act: 0.6698. Min Act: -0.0000

Data Index: 69376 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 0.8573. Min Range: -0.8573

Max Act: 0.7357. Min Act: -0.0000

Data Index: 333742 (C4 (Web Text))

Max Activating Token Index: 424

Text #8

Max Range: 0.8573. Min Range: -0.8573

Max Act: 0.6708. Min Act: -0.0000

Data Index: 655074 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 0.8573. Min Range: -0.8573

Max Act: 0.6679. Min Act: -0.0000

Data Index: 291941 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 0.8573. Min Range: -0.8573

Max Act: 0.6459. Min Act: -0.0000

Data Index: 362293 (C4 (Web Text))

Max Activating Token Index: 910

Text #11

Max Range: 0.8573. Min Range: -0.8573

Max Act: 0.6358. Min Act: -0.0000

Data Index: 1310552 (C4 (Web Text))

Max Activating Token Index: 411

Text #12

Max Range: 0.8573. Min Range: -0.8573

Max Act: 0.5454. Min Act: -0.0000

Data Index: 461009 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 0.8573. Min Range: -0.8573

Max Act: 0.6464. Min Act: -0.0000

Data Index: 58627 (C4 (Web Text))

Max Activating Token Index: 545

Text #14

Max Range: 0.8573. Min Range: -0.8573

Max Act: 0.6232. Min Act: -0.0000

Data Index: 234012 (C4 (Web Text))

Max Activating Token Index: 342

Text #15

Max Range: 0.8573. Min Range: -0.8573

Max Act: 0.6727. Min Act: -0.0000

Data Index: 1243873 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 0.8573. Min Range: -0.8573

Max Act: 0.6502. Min Act: -0.0000

Data Index: 152354 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 0.8573. Min Range: -0.8573

Max Act: 0.6766. Min Act: -0.0000

Data Index: 206895 (C4 (Web Text))

Max Activating Token Index: 984

Text #18

Max Range: 0.8573. Min Range: -0.8573

Max Act: 0.6247. Min Act: -0.0000

Data Index: 143132 (C4 (Web Text))

Max Activating Token Index: 337

Text #19

Max Range: 0.8573. Min Range: -0.8573

Max Act: 0.6479. Min Act: -0.0000

Data Index: 640956 (C4 (Web Text))

Max Activating Token Index: 105