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

Dataset: The Pile

Neuron 2125 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: 0.1021. Min Range: -0.1021

Max Act: 0.1021. Min Act: 0.0001

Data Index: 489690 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.1008. Min Act: 0.0001

Data Index: 1852854 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.1000. Min Act: 0.0000

Data Index: 804871 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0982. Min Act: 0.0000

Data Index: 1558641 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0942. Min Act: 0.0000

Data Index: 1628722 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0847. Min Act: 0.0001

Data Index: 404462 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0851. Min Act: 0.0001

Data Index: 499511 (The Pile)

Max Activating Token Index: 1014

Text #7

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0844. Min Act: 0.0001

Data Index: 389658 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0841. Min Act: 0.0000

Data Index: 459445 (The Pile)

Max Activating Token Index: 66

Text #9

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0838. Min Act: 0.0002

Data Index: 198659 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0810. Min Act: 0.0000

Data Index: 1135333 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0805. Min Act: -0.0000

Data Index: 1728227 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0802. Min Act: 0.0002

Data Index: 1847666 (The Pile)

Max Activating Token Index: 980

Text #13

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0792. Min Act: 0.0001

Data Index: 846087 (The Pile)

Max Activating Token Index: 39

Text #14

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0783. Min Act: 0.0000

Data Index: 169052 (The Pile)

Max Activating Token Index: 225

Text #15

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0781. Min Act: 0.0001

Data Index: 394944 (The Pile)

Max Activating Token Index: 983

Text #16

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0779. Min Act: 0.0001

Data Index: 666572 (The Pile)

Max Activating Token Index: 1022

Text #17

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0779. Min Act: 0.0000

Data Index: 1494714 (The Pile)

Max Activating Token Index: 29

Text #18

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0776. Min Act: 0.0000

Data Index: 178561 (The Pile)

Max Activating Token Index: 263

Text #19

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0744. Min Act: -0.0000

Data Index: 946490 (The Pile)

Max Activating Token Index: 1023