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

Dataset: The Pile

Neuron 3524 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.7598. Min Act: -0.0000

Data Index: 66264 (The Pile)

Max Activating Token Index: 15

Text #1

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.7618. Min Act: -0.0000

Data Index: 1452723 (The Pile)

Max Activating Token Index: 145

Text #2

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6377. Min Act: -0.0000

Data Index: 892251 (The Pile)

Max Activating Token Index: 69

Text #3

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.7268. Min Act: -0.0000

Data Index: 156424 (The Pile)

Max Activating Token Index: 44

Text #4

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6732. Min Act: -0.0000

Data Index: 138580 (The Pile)

Max Activating Token Index: 78

Text #5

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6981. Min Act: -0.0000

Data Index: 1725504 (The Pile)

Max Activating Token Index: 23

Text #6

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6778. Min Act: -0.0000

Data Index: 85454 (The Pile)

Max Activating Token Index: 190

Text #7

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6690. Min Act: -0.0000

Data Index: 113363 (The Pile)

Max Activating Token Index: 7

Text #8

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6844. Min Act: -0.0000

Data Index: 1451568 (The Pile)

Max Activating Token Index: 71

Text #9

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6636. Min Act: -0.0000

Data Index: 1784986 (The Pile)

Max Activating Token Index: 25

Text #10

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6846. Min Act: -0.0000

Data Index: 1957570 (The Pile)

Max Activating Token Index: 641

Text #11

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6637. Min Act: -0.0000

Data Index: 505398 (The Pile)

Max Activating Token Index: 123

Text #12

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6593. Min Act: -0.0000

Data Index: 1326959 (The Pile)

Max Activating Token Index: 4

Text #13

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.7008. Min Act: -0.0000

Data Index: 202245 (The Pile)

Max Activating Token Index: 357

Text #14

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6921. Min Act: -0.0000

Data Index: 1918816 (The Pile)

Max Activating Token Index: 21

Text #15

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6751. Min Act: -0.0000

Data Index: 754066 (The Pile)

Max Activating Token Index: 943

Text #16

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6662. Min Act: -0.0000

Data Index: 84180 (The Pile)

Max Activating Token Index: 8

Text #17

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6534. Min Act: -0.0000

Data Index: 681458 (The Pile)

Max Activating Token Index: 49

Text #18

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6326. Min Act: -0.0000

Data Index: 1931953 (The Pile)

Max Activating Token Index: 21

Text #19

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6838. Min Act: -0.0000

Data Index: 1292170 (The Pile)

Max Activating Token Index: 86