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

Dataset: The Pile

Neuron 74 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2307. Min Act: -0.0000

Data Index: 478804 (The Pile)

Max Activating Token Index: 156

Text #1

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2430. Min Act: -0.0000

Data Index: 272022 (The Pile)

Max Activating Token Index: 508

Text #2

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2417. Min Act: -0.0000

Data Index: 402263 (The Pile)

Max Activating Token Index: 12

Text #3

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2295. Min Act: -0.0000

Data Index: 914300 (The Pile)

Max Activating Token Index: 5

Text #4

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2313. Min Act: -0.0000

Data Index: 115170 (The Pile)

Max Activating Token Index: 10

Text #5

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2073. Min Act: -0.0001

Data Index: 30753 (The Pile)

Max Activating Token Index: 17

Text #6

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2109. Min Act: -0.0000

Data Index: 794799 (The Pile)

Max Activating Token Index: 740

Text #7

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2057. Min Act: -0.0001

Data Index: 1566910 (The Pile)

Max Activating Token Index: 5

Text #8

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.1980. Min Act: -0.0000

Data Index: 507806 (The Pile)

Max Activating Token Index: 12

Text #9

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2039. Min Act: -0.0000

Data Index: 366881 (The Pile)

Max Activating Token Index: 60

Text #10

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2098. Min Act: -0.0000

Data Index: 888348 (The Pile)

Max Activating Token Index: 6

Text #11

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.1992. Min Act: -0.0000

Data Index: 1044779 (The Pile)

Max Activating Token Index: 24

Text #12

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2001. Min Act: -0.0000

Data Index: 1756756 (The Pile)

Max Activating Token Index: 9

Text #13

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.1983. Min Act: -0.0000

Data Index: 550629 (The Pile)

Max Activating Token Index: 10

Text #14

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.1979. Min Act: -0.0000

Data Index: 985287 (The Pile)

Max Activating Token Index: 6

Text #15

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.1896. Min Act: -0.0000

Data Index: 224661 (The Pile)

Max Activating Token Index: 16

Text #16

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.1886. Min Act: -0.0000

Data Index: 1148244 (The Pile)

Max Activating Token Index: 21

Text #17

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.1954. Min Act: -0.0000

Data Index: 1131019 (The Pile)

Max Activating Token Index: 6

Text #18

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2010. Min Act: -0.0000

Data Index: 636084 (The Pile)

Max Activating Token Index: 454

Text #19

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.1931. Min Act: -0.0000

Data Index: 1305928 (The Pile)

Max Activating Token Index: 25