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

Dataset: The Pile

Neuron 786 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: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 442587 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 1946377 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 1019126 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 203877 (The Pile)

Max Activating Token Index: 559

Text #4

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 1997447 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 1461796 (The Pile)

Max Activating Token Index: 333

Text #6

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 584664 (The Pile)

Max Activating Token Index: 786

Text #7

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 1989945 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 1698231 (The Pile)

Max Activating Token Index: 7

Text #9

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 1711499 (The Pile)

Max Activating Token Index: 978

Text #10

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 1609914 (The Pile)

Max Activating Token Index: 1

Text #11

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 1598993 (The Pile)

Max Activating Token Index: 1

Text #12

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 290765 (The Pile)

Max Activating Token Index: 117

Text #13

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 1827427 (The Pile)

Max Activating Token Index: 968

Text #14

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 1522787 (The Pile)

Max Activating Token Index: 9

Text #15

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 1909535 (The Pile)

Max Activating Token Index: 55

Text #16

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 587330 (The Pile)

Max Activating Token Index: 988

Text #17

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 461042 (The Pile)

Max Activating Token Index: 8

Text #18

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 195850 (The Pile)

Max Activating Token Index: 1003

Text #19

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 1835082 (The Pile)

Max Activating Token Index: 1