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

Dataset: The Pile

Neuron 4194 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: 0.5283. Min Range: -0.5283

Max Act: 0.5283. Min Act: -0.0000

Data Index: 708887 (The Pile)

Max Activating Token Index: 937

Text #1

Max Range: 0.5283. Min Range: -0.5283

Max Act: 0.5266. Min Act: -0.0000

Data Index: 753997 (The Pile)

Max Activating Token Index: 434

Text #2

Max Range: 0.5283. Min Range: -0.5283

Max Act: 0.5182. Min Act: -0.0000

Data Index: 837764 (The Pile)

Max Activating Token Index: 994

Text #3

Max Range: 0.5283. Min Range: -0.5283

Max Act: 0.5076. Min Act: -0.0000

Data Index: 1702493 (The Pile)

Max Activating Token Index: 21

Text #4

Max Range: 0.5283. Min Range: -0.5283

Max Act: 0.5210. Min Act: -0.0000

Data Index: 1321844 (The Pile)

Max Activating Token Index: 123

Text #5

Max Range: 0.5283. Min Range: -0.5283

Max Act: 0.4507. Min Act: -0.0000

Data Index: 1833590 (The Pile)

Max Activating Token Index: 754

Text #6

Max Range: 0.5283. Min Range: -0.5283

Max Act: 0.5089. Min Act: -0.0000

Data Index: 1035971 (The Pile)

Max Activating Token Index: 871

Text #7

Max Range: 0.5283. Min Range: -0.5283

Max Act: 0.4863. Min Act: -0.0000

Data Index: 789007 (The Pile)

Max Activating Token Index: 110

Text #8

Max Range: 0.5283. Min Range: -0.5283

Max Act: 0.4807. Min Act: -0.0000

Data Index: 309084 (The Pile)

Max Activating Token Index: 43

Text #9

Max Range: 0.5283. Min Range: -0.5283

Max Act: 0.4713. Min Act: -0.0000

Data Index: 1350538 (The Pile)

Max Activating Token Index: 860

Text #10

Max Range: 0.5283. Min Range: -0.5283

Max Act: 0.4925. Min Act: -0.0000

Data Index: 364373 (The Pile)

Max Activating Token Index: 70

Text #11

Max Range: 0.5283. Min Range: -0.5283

Max Act: 0.4755. Min Act: -0.0000

Data Index: 998877 (The Pile)

Max Activating Token Index: 122

Text #12

Max Range: 0.5283. Min Range: -0.5283

Max Act: 0.4547. Min Act: -0.0000

Data Index: 561904 (The Pile)

Max Activating Token Index: 963

Text #13

Max Range: 0.5283. Min Range: -0.5283

Max Act: 0.4709. Min Act: -0.0000

Data Index: 938309 (The Pile)

Max Activating Token Index: 324

Text #14

Max Range: 0.5283. Min Range: -0.5283

Max Act: 0.4580. Min Act: -0.0000

Data Index: 850307 (The Pile)

Max Activating Token Index: 844

Text #15

Max Range: 0.5283. Min Range: -0.5283

Max Act: 0.4482. Min Act: -0.0000

Data Index: 1751856 (The Pile)

Max Activating Token Index: 737

Text #16

Max Range: 0.5283. Min Range: -0.5283

Max Act: 0.4619. Min Act: -0.0000

Data Index: 1631035 (The Pile)

Max Activating Token Index: 926

Text #17

Max Range: 0.5283. Min Range: -0.5283

Max Act: 0.4255. Min Act: -0.0000

Data Index: 1127359 (The Pile)

Max Activating Token Index: 718

Text #18

Max Range: 0.5283. Min Range: -0.5283

Max Act: 0.4390. Min Act: -0.0000

Data Index: 1033974 (The Pile)

Max Activating Token Index: 920

Text #19

Max Range: 0.5283. Min Range: -0.5283

Max Act: 0.4390. Min Act: -0.0000

Data Index: 1419813 (The Pile)

Max Activating Token Index: 468