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

Dataset: The Pile

Neuron 2467 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.3160. Min Act: -0.0000

Data Index: 1304261 (The Pile)

Max Activating Token Index: 149

Text #1

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.3294. Min Act: -0.0000

Data Index: 1695540 (The Pile)

Max Activating Token Index: 138

Text #2

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.3142. Min Act: -0.0000

Data Index: 541012 (The Pile)

Max Activating Token Index: 914

Text #3

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2925. Min Act: -0.0000

Data Index: 1490089 (The Pile)

Max Activating Token Index: 44

Text #4

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.3047. Min Act: -0.0000

Data Index: 463836 (The Pile)

Max Activating Token Index: 544

Text #5

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.3015. Min Act: -0.0000

Data Index: 1399774 (The Pile)

Max Activating Token Index: 730

Text #6

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2990. Min Act: -0.0000

Data Index: 847831 (The Pile)

Max Activating Token Index: 148

Text #7

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.3009. Min Act: -0.0000

Data Index: 1835171 (The Pile)

Max Activating Token Index: 138

Text #8

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.3005. Min Act: -0.0000

Data Index: 1452657 (The Pile)

Max Activating Token Index: 607

Text #9

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.3145. Min Act: -0.0000

Data Index: 1610929 (The Pile)

Max Activating Token Index: 580

Text #10

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2819. Min Act: -0.0000

Data Index: 192660 (The Pile)

Max Activating Token Index: 146

Text #11

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.3027. Min Act: -0.0000

Data Index: 724531 (The Pile)

Max Activating Token Index: 32

Text #12

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2823. Min Act: -0.0000

Data Index: 319117 (The Pile)

Max Activating Token Index: 272

Text #13

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2933. Min Act: -0.0000

Data Index: 843740 (The Pile)

Max Activating Token Index: 84

Text #14

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2826. Min Act: -0.0000

Data Index: 963428 (The Pile)

Max Activating Token Index: 836

Text #15

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2799. Min Act: -0.0000

Data Index: 1888066 (The Pile)

Max Activating Token Index: 127

Text #16

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2703. Min Act: -0.0000

Data Index: 182880 (The Pile)

Max Activating Token Index: 983

Text #17

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2778. Min Act: -0.0000

Data Index: 1861379 (The Pile)

Max Activating Token Index: 64

Text #18

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2944. Min Act: -0.0000

Data Index: 1699476 (The Pile)

Max Activating Token Index: 139

Text #19

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2768. Min Act: -0.0000

Data Index: 266264 (The Pile)

Max Activating Token Index: 32