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

Dataset: The Pile

Neuron 2925 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.7754. Min Act: -0.0000

Data Index: 482984 (The Pile)

Max Activating Token Index: 801

Text #1

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.5611. Min Act: -0.0000

Data Index: 323260 (The Pile)

Max Activating Token Index: 414

Text #2

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.6022. Min Act: -0.0000

Data Index: 1008913 (The Pile)

Max Activating Token Index: 46

Text #3

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.5578. Min Act: -0.0000

Data Index: 1874261 (The Pile)

Max Activating Token Index: 345

Text #4

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.6345. Min Act: -0.0000

Data Index: 1978328 (The Pile)

Max Activating Token Index: 452

Text #5

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.5295. Min Act: -0.0000

Data Index: 1854035 (The Pile)

Max Activating Token Index: 45

Text #6

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.5314. Min Act: -0.0000

Data Index: 1264469 (The Pile)

Max Activating Token Index: 131

Text #7

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.5087. Min Act: -0.0000

Data Index: 1231634 (The Pile)

Max Activating Token Index: 934

Text #8

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.4061. Min Act: -0.0000

Data Index: 389343 (The Pile)

Max Activating Token Index: 737

Text #9

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.3937. Min Act: -0.0000

Data Index: 353852 (The Pile)

Max Activating Token Index: 923

Text #10

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.4649. Min Act: -0.0000

Data Index: 1166559 (The Pile)

Max Activating Token Index: 566

Text #11

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.5497. Min Act: -0.0000

Data Index: 682176 (The Pile)

Max Activating Token Index: 113

Text #12

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.4548. Min Act: -0.0000

Data Index: 1169468 (The Pile)

Max Activating Token Index: 566

Text #13

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.3838. Min Act: -0.0000

Data Index: 672973 (The Pile)

Max Activating Token Index: 869

Text #14

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.5277. Min Act: -0.0000

Data Index: 1610141 (The Pile)

Max Activating Token Index: 407

Text #15

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.4118. Min Act: -0.0000

Data Index: 229997 (The Pile)

Max Activating Token Index: 17

Text #16

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.3948. Min Act: -0.0000

Data Index: 1474933 (The Pile)

Max Activating Token Index: 424

Text #17

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.4155. Min Act: -0.0000

Data Index: 936569 (The Pile)

Max Activating Token Index: 40

Text #18

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.4095. Min Act: -0.0000

Data Index: 1709721 (The Pile)

Max Activating Token Index: 82

Text #19

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.3667. Min Act: -0.0000

Data Index: 1630990 (The Pile)

Max Activating Token Index: 56