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

Dataset: The Pile

Neuron 837 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.7739. Min Act: -0.0000

Data Index: 1982971 (The Pile)

Max Activating Token Index: 549

Text #1

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.7724. Min Act: -0.0000

Data Index: 1697244 (The Pile)

Max Activating Token Index: 887

Text #2

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.7909. Min Act: -0.0000

Data Index: 1763099 (The Pile)

Max Activating Token Index: 82

Text #3

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.7145. Min Act: -0.0000

Data Index: 1024144 (The Pile)

Max Activating Token Index: 499

Text #4

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.7067. Min Act: -0.0000

Data Index: 94211 (The Pile)

Max Activating Token Index: 834

Text #5

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.6447. Min Act: -0.0000

Data Index: 118885 (The Pile)

Max Activating Token Index: 299

Text #6

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.6878. Min Act: -0.0000

Data Index: 939618 (The Pile)

Max Activating Token Index: 496

Text #7

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.6549. Min Act: -0.0000

Data Index: 1054248 (The Pile)

Max Activating Token Index: 930

Text #8

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.5997. Min Act: -0.0000

Data Index: 838376 (The Pile)

Max Activating Token Index: 211

Text #9

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.6316. Min Act: -0.0000

Data Index: 1189723 (The Pile)

Max Activating Token Index: 506

Text #10

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.6088. Min Act: -0.0000

Data Index: 875375 (The Pile)

Max Activating Token Index: 842

Text #11

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.6227. Min Act: -0.0000

Data Index: 1629365 (The Pile)

Max Activating Token Index: 948

Text #12

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.6068. Min Act: -0.0000

Data Index: 1427237 (The Pile)

Max Activating Token Index: 1001

Text #13

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.6216. Min Act: -0.0000

Data Index: 78877 (The Pile)

Max Activating Token Index: 315

Text #14

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.5972. Min Act: -0.0000

Data Index: 650660 (The Pile)

Max Activating Token Index: 950

Text #15

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.5967. Min Act: -0.0000

Data Index: 319845 (The Pile)

Max Activating Token Index: 838

Text #16

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.5953. Min Act: -0.0000

Data Index: 524921 (The Pile)

Max Activating Token Index: 391

Text #17

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.6694. Min Act: -0.0000

Data Index: 285877 (The Pile)

Max Activating Token Index: 944

Text #18

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.6303. Min Act: -0.0000

Data Index: 1731898 (The Pile)

Max Activating Token Index: 854

Text #19

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.6171. Min Act: -0.0000

Data Index: 989818 (The Pile)

Max Activating Token Index: 621