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

Dataset: The Pile

Neuron 3051 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: 0.1016. Min Range: -0.1016

Max Act: 0.1016. Min Act: 0.0002

Data Index: 1854575 (The Pile)

Max Activating Token Index: 8

Text #1

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0866. Min Act: -0.0000

Data Index: 421001 (The Pile)

Max Activating Token Index: 65

Text #2

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0851. Min Act: 0.0001

Data Index: 1417132 (The Pile)

Max Activating Token Index: 578

Text #3

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0847. Min Act: 0.0001

Data Index: 1453967 (The Pile)

Max Activating Token Index: 19

Text #4

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0799. Min Act: 0.0001

Data Index: 1717748 (The Pile)

Max Activating Token Index: 33

Text #5

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0793. Min Act: 0.0002

Data Index: 318294 (The Pile)

Max Activating Token Index: 369

Text #6

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0815. Min Act: 0.0000

Data Index: 1498668 (The Pile)

Max Activating Token Index: 75

Text #7

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0807. Min Act: 0.0000

Data Index: 1993328 (The Pile)

Max Activating Token Index: 10

Text #8

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0798. Min Act: 0.0001

Data Index: 119456 (The Pile)

Max Activating Token Index: 46

Text #9

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0796. Min Act: 0.0000

Data Index: 428903 (The Pile)

Max Activating Token Index: 75

Text #10

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0792. Min Act: 0.0000

Data Index: 263449 (The Pile)

Max Activating Token Index: 903

Text #11

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0793. Min Act: -0.0000

Data Index: 1064331 (The Pile)

Max Activating Token Index: 75

Text #12

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0792. Min Act: 0.0002

Data Index: 1385809 (The Pile)

Max Activating Token Index: 399

Text #13

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0788. Min Act: 0.0001

Data Index: 607645 (The Pile)

Max Activating Token Index: 425

Text #14

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0787. Min Act: 0.0001

Data Index: 1926188 (The Pile)

Max Activating Token Index: 95

Text #15

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0784. Min Act: 0.0004

Data Index: 993313 (The Pile)

Max Activating Token Index: 48

Text #16

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0782. Min Act: 0.0001

Data Index: 1860338 (The Pile)

Max Activating Token Index: 668

Text #17

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0780. Min Act: 0.0000

Data Index: 746900 (The Pile)

Max Activating Token Index: 381

Text #18

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0752. Min Act: 0.0002

Data Index: 1838488 (The Pile)

Max Activating Token Index: 697

Text #19

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0776. Min Act: 0.0002

Data Index: 1307206 (The Pile)

Max Activating Token Index: 433