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

Dataset: The Pile

Neuron 3952 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1628. Min Act: -0.0000

Data Index: 1211567 (The Pile)

Max Activating Token Index: 46

Text #1

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1386. Min Act: -0.0000

Data Index: 1652194 (The Pile)

Max Activating Token Index: 68

Text #2

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1060. Min Act: -0.0000

Data Index: 10519 (The Pile)

Max Activating Token Index: 118

Text #3

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1155. Min Act: -0.0000

Data Index: 772200 (The Pile)

Max Activating Token Index: 840

Text #4

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.0851. Min Act: -0.0000

Data Index: 1911974 (The Pile)

Max Activating Token Index: 1015

Text #5

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.0925. Min Act: -0.0000

Data Index: 1169098 (The Pile)

Max Activating Token Index: 963

Text #6

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.0890. Min Act: -0.0000

Data Index: 1517914 (The Pile)

Max Activating Token Index: 785

Text #7

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.0917. Min Act: -0.0000

Data Index: 399221 (The Pile)

Max Activating Token Index: 81

Text #8

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.0945. Min Act: -0.0000

Data Index: 1868675 (The Pile)

Max Activating Token Index: 75

Text #9

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.0886. Min Act: -0.0000

Data Index: 260406 (The Pile)

Max Activating Token Index: 82

Text #10

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.0865. Min Act: -0.0000

Data Index: 655120 (The Pile)

Max Activating Token Index: 112

Text #11

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.0971. Min Act: -0.0000

Data Index: 532564 (The Pile)

Max Activating Token Index: 900

Text #12

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.0939. Min Act: -0.0000

Data Index: 1491908 (The Pile)

Max Activating Token Index: 1002

Text #13

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.0999. Min Act: -0.0000

Data Index: 965161 (The Pile)

Max Activating Token Index: 897

Text #14

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.0890. Min Act: -0.0000

Data Index: 1084231 (The Pile)

Max Activating Token Index: 437

Text #15

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1025. Min Act: -0.0000

Data Index: 1254257 (The Pile)

Max Activating Token Index: 119

Text #16

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.0848. Min Act: -0.0000

Data Index: 408554 (The Pile)

Max Activating Token Index: 132

Text #17

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.0836. Min Act: -0.0000

Data Index: 727756 (The Pile)

Max Activating Token Index: 55

Text #18

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.0790. Min Act: -0.0000

Data Index: 1040252 (The Pile)

Max Activating Token Index: 630

Text #19

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.0794. Min Act: -0.0000

Data Index: 397916 (The Pile)

Max Activating Token Index: 901