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

Dataset: The Pile

Neuron 4483 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: 0.0854. Min Range: -0.0854

Max Act: 0.0854. Min Act: -0.0000

Data Index: 776240 (The Pile)

Max Activating Token Index: 5

Text #1

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0853. Min Act: -0.0000

Data Index: 1160081 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0834. Min Act: -0.0000

Data Index: 1840020 (The Pile)

Max Activating Token Index: 16

Text #3

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0824. Min Act: -0.0000

Data Index: 45694 (The Pile)

Max Activating Token Index: 7

Text #4

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0819. Min Act: -0.0000

Data Index: 106061 (The Pile)

Max Activating Token Index: 587

Text #5

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0803. Min Act: -0.0000

Data Index: 716927 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0792. Min Act: -0.0000

Data Index: 1366888 (The Pile)

Max Activating Token Index: 2

Text #7

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0792. Min Act: -0.0000

Data Index: 433314 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0792. Min Act: -0.0000

Data Index: 1285345 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0789. Min Act: -0.0000

Data Index: 334586 (The Pile)

Max Activating Token Index: 7

Text #10

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0787. Min Act: -0.0000

Data Index: 1611938 (The Pile)

Max Activating Token Index: 940

Text #11

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0782. Min Act: -0.0000

Data Index: 849978 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0780. Min Act: -0.0000

Data Index: 534382 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0777. Min Act: -0.0000

Data Index: 1375992 (The Pile)

Max Activating Token Index: 991

Text #14

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0750. Min Act: -0.0000

Data Index: 1467533 (The Pile)

Max Activating Token Index: 959

Text #15

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0777. Min Act: -0.0000

Data Index: 570235 (The Pile)

Max Activating Token Index: 7

Text #16

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0775. Min Act: -0.0000

Data Index: 1891808 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0804. Min Act: -0.0000

Data Index: 1922344 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0775. Min Act: -0.0000

Data Index: 1661322 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0747. Min Act: -0.0000

Data Index: 1060645 (The Pile)

Max Activating Token Index: 1016