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

Dataset: The Pile

Neuron 4122 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0954. Min Act: -0.0000

Data Index: 1561510 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0930. Min Act: -0.0000

Data Index: 1828027 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0931. Min Act: -0.0000

Data Index: 312380 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0908. Min Act: -0.0000

Data Index: 1997744 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0891. Min Act: -0.0000

Data Index: 793779 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0876. Min Act: -0.0000

Data Index: 829988 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0871. Min Act: -0.0000

Data Index: 726563 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0865. Min Act: -0.0000

Data Index: 862232 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0862. Min Act: -0.0000

Data Index: 93660 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0859. Min Act: -0.0000

Data Index: 1245875 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0857. Min Act: -0.0000

Data Index: 1064794 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0854. Min Act: -0.0000

Data Index: 1209556 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0855. Min Act: -0.0000

Data Index: 169327 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0854. Min Act: -0.0000

Data Index: 1636987 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0855. Min Act: -0.0000

Data Index: 865899 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0848. Min Act: -0.0000

Data Index: 1928491 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0843. Min Act: -0.0000

Data Index: 832712 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0873. Min Act: -0.0000

Data Index: 1594417 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0841. Min Act: -0.0000

Data Index: 41178 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0840. Min Act: -0.0000

Data Index: 117008 (The Pile)

Max Activating Token Index: 1023