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

Dataset: The Pile

Neuron 2772 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: 0.0003

Data Index: 641389 (The Pile)

Max Activating Token Index: 91

Text #1

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.1002. Min Act: 0.0003

Data Index: 702466 (The Pile)

Max Activating Token Index: 398

Text #2

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0943. Min Act: 0.0003

Data Index: 795786 (The Pile)

Max Activating Token Index: 61

Text #3

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0910. Min Act: 0.0003

Data Index: 1755703 (The Pile)

Max Activating Token Index: 899

Text #4

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0890. Min Act: 0.0001

Data Index: 1798245 (The Pile)

Max Activating Token Index: 54

Text #5

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0914. Min Act: 0.0003

Data Index: 110541 (The Pile)

Max Activating Token Index: 15

Text #6

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0853. Min Act: -0.0000

Data Index: 739061 (The Pile)

Max Activating Token Index: 5

Text #7

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0774. Min Act: -0.0000

Data Index: 185335 (The Pile)

Max Activating Token Index: 154

Text #8

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0800. Min Act: -0.0000

Data Index: 209340 (The Pile)

Max Activating Token Index: 91

Text #9

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0765. Min Act: 0.0003

Data Index: 629453 (The Pile)

Max Activating Token Index: 68

Text #10

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0735. Min Act: -0.0000

Data Index: 1382073 (The Pile)

Max Activating Token Index: 13

Text #11

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0728. Min Act: 0.0003

Data Index: 740447 (The Pile)

Max Activating Token Index: 785

Text #12

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0727. Min Act: 0.0000

Data Index: 1370497 (The Pile)

Max Activating Token Index: 1001

Text #13

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0723. Min Act: 0.0001

Data Index: 706766 (The Pile)

Max Activating Token Index: 15

Text #14

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0724. Min Act: -0.0000

Data Index: 1750379 (The Pile)

Max Activating Token Index: 32

Text #15

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0744. Min Act: 0.0003

Data Index: 1045366 (The Pile)

Max Activating Token Index: 1011

Text #16

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0714. Min Act: -0.0000

Data Index: 1010442 (The Pile)

Max Activating Token Index: 37

Text #17

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0708. Min Act: 0.0003

Data Index: 1808971 (The Pile)

Max Activating Token Index: 23

Text #18

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0707. Min Act: -0.0000

Data Index: 1685350 (The Pile)

Max Activating Token Index: 26

Text #19

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0729. Min Act: 0.0000

Data Index: 344384 (The Pile)

Max Activating Token Index: 31