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

Dataset: The Pile

Neuron 4330 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.4874. Min Range: -7.4874

Max Act: 7.4874. Min Act: -0.0000

Data Index: 1329231 (The Pile)

Max Activating Token Index: 859

Text #1

Max Range: 7.4874. Min Range: -7.4874

Max Act: 7.2024. Min Act: -0.0000

Data Index: 712563 (The Pile)

Max Activating Token Index: 193

Text #2

Max Range: 7.4874. Min Range: -7.4874

Max Act: 7.2826. Min Act: -0.0000

Data Index: 1257459 (The Pile)

Max Activating Token Index: 324

Text #3

Max Range: 7.4874. Min Range: -7.4874

Max Act: 6.8500. Min Act: -0.0000

Data Index: 634726 (The Pile)

Max Activating Token Index: 573

Text #4

Max Range: 7.4874. Min Range: -7.4874

Max Act: 6.0661. Min Act: -0.0000

Data Index: 1888634 (The Pile)

Max Activating Token Index: 363

Text #5

Max Range: 7.4874. Min Range: -7.4874

Max Act: 6.5228. Min Act: -0.0000

Data Index: 345377 (The Pile)

Max Activating Token Index: 146

Text #6

Max Range: 7.4874. Min Range: -7.4874

Max Act: 6.5254. Min Act: -0.0000

Data Index: 173566 (The Pile)

Max Activating Token Index: 56

Text #7

Max Range: 7.4874. Min Range: -7.4874

Max Act: 5.9587. Min Act: -0.0000

Data Index: 1489919 (The Pile)

Max Activating Token Index: 771

Text #8

Max Range: 7.4874. Min Range: -7.4874

Max Act: 6.0514. Min Act: -0.0000

Data Index: 235939 (The Pile)

Max Activating Token Index: 119

Text #9

Max Range: 7.4874. Min Range: -7.4874

Max Act: 6.1349. Min Act: -0.0000

Data Index: 1979208 (The Pile)

Max Activating Token Index: 789

Text #10

Max Range: 7.4874. Min Range: -7.4874

Max Act: 6.2088. Min Act: -0.0000

Data Index: 1713854 (The Pile)

Max Activating Token Index: 959

Text #11

Max Range: 7.4874. Min Range: -7.4874

Max Act: 6.1527. Min Act: -0.0000

Data Index: 982600 (The Pile)

Max Activating Token Index: 520

Text #12

Max Range: 7.4874. Min Range: -7.4874

Max Act: 7.1077. Min Act: -0.0000

Data Index: 1430660 (The Pile)

Max Activating Token Index: 842

Text #13

Max Range: 7.4874. Min Range: -7.4874

Max Act: 5.1256. Min Act: -0.0000

Data Index: 61619 (The Pile)

Max Activating Token Index: 36

Text #14

Max Range: 7.4874. Min Range: -7.4874

Max Act: 4.5240. Min Act: -0.0000

Data Index: 596413 (The Pile)

Max Activating Token Index: 552

Text #15

Max Range: 7.4874. Min Range: -7.4874

Max Act: 4.9502. Min Act: -0.0000

Data Index: 253534 (The Pile)

Max Activating Token Index: 944

Text #16

Max Range: 7.4874. Min Range: -7.4874

Max Act: 3.9886. Min Act: -0.0000

Data Index: 684635 (The Pile)

Max Activating Token Index: 249

Text #17

Max Range: 7.4874. Min Range: -7.4874

Max Act: 3.8853. Min Act: -0.0000

Data Index: 1979865 (The Pile)

Max Activating Token Index: 118

Text #18

Max Range: 7.4874. Min Range: -7.4874

Max Act: 4.0046. Min Act: -0.0000

Data Index: 21308 (The Pile)

Max Activating Token Index: 540

Text #19

Max Range: 7.4874. Min Range: -7.4874

Max Act: 3.2472. Min Act: -0.0000

Data Index: 386721 (The Pile)

Max Activating Token Index: 758