Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 246 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.4851. Min Act: -0.0000

Data Index: 1064348 (The Pile)

Max Activating Token Index: 932

Text #1

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.4966. Min Act: -0.0000

Data Index: 386261 (The Pile)

Max Activating Token Index: 439

Text #2

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.4731. Min Act: -0.0000

Data Index: 1837239 (The Pile)

Max Activating Token Index: 360

Text #3

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.4423. Min Act: -0.0000

Data Index: 1812526 (The Pile)

Max Activating Token Index: 1008

Text #4

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.4570. Min Act: -0.0000

Data Index: 1023058 (The Pile)

Max Activating Token Index: 248

Text #5

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3817. Min Act: -0.0000

Data Index: 1227794 (The Pile)

Max Activating Token Index: 58

Text #6

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3884. Min Act: -0.0001

Data Index: 1311689 (The Pile)

Max Activating Token Index: 321

Text #7

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.4027. Min Act: -0.0000

Data Index: 584159 (The Pile)

Max Activating Token Index: 616

Text #8

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.4021. Min Act: -0.0001

Data Index: 1571346 (The Pile)

Max Activating Token Index: 696

Text #9

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.4106. Min Act: -0.0000

Data Index: 7426 (The Pile)

Max Activating Token Index: 383

Text #10

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3935. Min Act: -0.0000

Data Index: 258304 (The Pile)

Max Activating Token Index: 663

Text #11

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.4068. Min Act: -0.0000

Data Index: 1965382 (The Pile)

Max Activating Token Index: 453

Text #12

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3616. Min Act: -0.0000

Data Index: 1277871 (The Pile)

Max Activating Token Index: 630

Text #13

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3542. Min Act: -0.0000

Data Index: 508357 (The Pile)

Max Activating Token Index: 154

Text #14

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3902. Min Act: -0.0000

Data Index: 1326889 (The Pile)

Max Activating Token Index: 900

Text #15

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3732. Min Act: -0.0000

Data Index: 1380298 (The Pile)

Max Activating Token Index: 410

Text #16

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3673. Min Act: -0.0000

Data Index: 279333 (The Pile)

Max Activating Token Index: 981

Text #17

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3874. Min Act: -0.0000

Data Index: 787666 (The Pile)

Max Activating Token Index: 74

Text #18

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3521. Min Act: -0.0000

Data Index: 1882191 (The Pile)

Max Activating Token Index: 409

Text #19

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3804. Min Act: 0.0000

Data Index: 402187 (The Pile)

Max Activating Token Index: 1016