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

Dataset: The Pile

Neuron 2433 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.1180. Min Act: -0.0000

Data Index: 1953309 (The Pile)

Max Activating Token Index: 704

Text #1

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.1280. Min Act: -0.0000

Data Index: 1859415 (The Pile)

Max Activating Token Index: 487

Text #2

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.1097. Min Act: -0.0000

Data Index: 1055614 (The Pile)

Max Activating Token Index: 12

Text #3

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0943. Min Act: -0.0000

Data Index: 1605854 (The Pile)

Max Activating Token Index: 395

Text #4

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.1006. Min Act: -0.0000

Data Index: 595260 (The Pile)

Max Activating Token Index: 200

Text #5

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0943. Min Act: -0.0000

Data Index: 618350 (The Pile)

Max Activating Token Index: 308

Text #6

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.1008. Min Act: -0.0000

Data Index: 35503 (The Pile)

Max Activating Token Index: 553

Text #7

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0896. Min Act: -0.0000

Data Index: 1720144 (The Pile)

Max Activating Token Index: 110

Text #8

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0874. Min Act: -0.0000

Data Index: 822973 (The Pile)

Max Activating Token Index: 1008

Text #9

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0859. Min Act: -0.0000

Data Index: 1132507 (The Pile)

Max Activating Token Index: 687

Text #10

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0862. Min Act: -0.0000

Data Index: 1818711 (The Pile)

Max Activating Token Index: 443

Text #11

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0811. Min Act: -0.0000

Data Index: 1550366 (The Pile)

Max Activating Token Index: 779

Text #12

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0751. Min Act: -0.0000

Data Index: 1708941 (The Pile)

Max Activating Token Index: 727

Text #13

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0786. Min Act: -0.0000

Data Index: 1953501 (The Pile)

Max Activating Token Index: 575

Text #14

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0805. Min Act: -0.0000

Data Index: 856280 (The Pile)

Max Activating Token Index: 847

Text #15

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0829. Min Act: -0.0000

Data Index: 1712970 (The Pile)

Max Activating Token Index: 768

Text #16

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0763. Min Act: -0.0000

Data Index: 1665148 (The Pile)

Max Activating Token Index: 981

Text #17

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0763. Min Act: -0.0000

Data Index: 188157 (The Pile)

Max Activating Token Index: 564

Text #18

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0793. Min Act: -0.0000

Data Index: 1176758 (The Pile)

Max Activating Token Index: 220

Text #19

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0779. Min Act: -0.0000

Data Index: 1733128 (The Pile)

Max Activating Token Index: 335