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

Dataset: The Pile

Neuron 2430 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: 0.5349. Min Range: -0.5349

Max Act: 0.5188. Min Act: -0.0000

Data Index: 295715 (The Pile)

Max Activating Token Index: 863

Text #1

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.5349. Min Act: -0.0000

Data Index: 352551 (The Pile)

Max Activating Token Index: 835

Text #2

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.4860. Min Act: -0.0000

Data Index: 1570967 (The Pile)

Max Activating Token Index: 1010

Text #3

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.4637. Min Act: -0.0000

Data Index: 325376 (The Pile)

Max Activating Token Index: 937

Text #4

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.4053. Min Act: -0.0000

Data Index: 810123 (The Pile)

Max Activating Token Index: 164

Text #5

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.3892. Min Act: -0.0000

Data Index: 161337 (The Pile)

Max Activating Token Index: 566

Text #6

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.3238. Min Act: -0.0000

Data Index: 1835872 (The Pile)

Max Activating Token Index: 971

Text #7

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.3471. Min Act: -0.0000

Data Index: 734373 (The Pile)

Max Activating Token Index: 865

Text #8

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.3440. Min Act: -0.0000

Data Index: 313880 (The Pile)

Max Activating Token Index: 1017

Text #9

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.3635. Min Act: -0.0000

Data Index: 496854 (The Pile)

Max Activating Token Index: 364

Text #10

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.3435. Min Act: -0.0000

Data Index: 1391063 (The Pile)

Max Activating Token Index: 967

Text #11

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.3100. Min Act: -0.0000

Data Index: 1573562 (The Pile)

Max Activating Token Index: 859

Text #12

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.2896. Min Act: -0.0000

Data Index: 913204 (The Pile)

Max Activating Token Index: 261

Text #13

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.2966. Min Act: -0.0000

Data Index: 346327 (The Pile)

Max Activating Token Index: 857

Text #14

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.3207. Min Act: -0.0000

Data Index: 1950420 (The Pile)

Max Activating Token Index: 754

Text #15

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.2941. Min Act: -0.0000

Data Index: 1331578 (The Pile)

Max Activating Token Index: 907

Text #16

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.2979. Min Act: -0.0000

Data Index: 534255 (The Pile)

Max Activating Token Index: 458

Text #17

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.2673. Min Act: -0.0000

Data Index: 1068781 (The Pile)

Max Activating Token Index: 599

Text #18

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.2914. Min Act: -0.0000

Data Index: 530357 (The Pile)

Max Activating Token Index: 831

Text #19

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.2886. Min Act: -0.0000

Data Index: 1671374 (The Pile)

Max Activating Token Index: 752