Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 957 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.2110. Min Act: -0.0000

Data Index: 723691 (The Pile)

Max Activating Token Index: 860

Text #1

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.2167. Min Act: -0.0000

Data Index: 1464619 (The Pile)

Max Activating Token Index: 460

Text #2

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.2177. Min Act: -0.0000

Data Index: 1952488 (The Pile)

Max Activating Token Index: 52

Text #3

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.1985. Min Act: -0.0000

Data Index: 1338268 (The Pile)

Max Activating Token Index: 206

Text #4

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.2048. Min Act: -0.0000

Data Index: 1096349 (The Pile)

Max Activating Token Index: 983

Text #5

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.1998. Min Act: -0.0000

Data Index: 95487 (The Pile)

Max Activating Token Index: 84

Text #6

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.1996. Min Act: -0.0000

Data Index: 1766138 (The Pile)

Max Activating Token Index: 988

Text #7

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.1995. Min Act: -0.0000

Data Index: 1409876 (The Pile)

Max Activating Token Index: 961

Text #8

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.1938. Min Act: -0.0000

Data Index: 393498 (The Pile)

Max Activating Token Index: 196

Text #9

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.1936. Min Act: -0.0000

Data Index: 1137525 (The Pile)

Max Activating Token Index: 798

Text #10

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.1927. Min Act: -0.0000

Data Index: 788051 (The Pile)

Max Activating Token Index: 1008

Text #11

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.1924. Min Act: -0.0000

Data Index: 754368 (The Pile)

Max Activating Token Index: 425

Text #12

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.1800. Min Act: -0.0000

Data Index: 532663 (The Pile)

Max Activating Token Index: 127

Text #13

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.1913. Min Act: -0.0000

Data Index: 583766 (The Pile)

Max Activating Token Index: 71

Text #14

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.1909. Min Act: -0.0000

Data Index: 325943 (The Pile)

Max Activating Token Index: 76

Text #15

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.1897. Min Act: -0.0000

Data Index: 1977344 (The Pile)

Max Activating Token Index: 972

Text #16

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.1907. Min Act: -0.0000

Data Index: 398454 (The Pile)

Max Activating Token Index: 755

Text #17

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.1867. Min Act: -0.0000

Data Index: 1758809 (The Pile)

Max Activating Token Index: 315

Text #18

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.1870. Min Act: -0.0000

Data Index: 599546 (The Pile)

Max Activating Token Index: 558

Text #19

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.1865. Min Act: -0.0000

Data Index: 1595046 (The Pile)

Max Activating Token Index: 501