Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3928 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.9623. Min Act: -0.0000

Data Index: 1719602 (The Pile)

Max Activating Token Index: 47

Text #1

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.8449. Min Act: -0.0000

Data Index: 1442179 (The Pile)

Max Activating Token Index: 45

Text #2

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.9374. Min Act: -0.0000

Data Index: 1087678 (The Pile)

Max Activating Token Index: 37

Text #3

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.8707. Min Act: -0.0000

Data Index: 1697214 (The Pile)

Max Activating Token Index: 33

Text #4

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.6624. Min Act: -0.0000

Data Index: 649850 (The Pile)

Max Activating Token Index: 962

Text #5

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.7518. Min Act: -0.0000

Data Index: 1190311 (The Pile)

Max Activating Token Index: 695

Text #6

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.8196. Min Act: -0.0000

Data Index: 1750062 (The Pile)

Max Activating Token Index: 76

Text #7

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.7529. Min Act: -0.0000

Data Index: 1256675 (The Pile)

Max Activating Token Index: 10

Text #8

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.7363. Min Act: -0.0000

Data Index: 1766081 (The Pile)

Max Activating Token Index: 49

Text #9

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.6882. Min Act: -0.0000

Data Index: 1883617 (The Pile)

Max Activating Token Index: 34

Text #10

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.6422. Min Act: -0.0000

Data Index: 1840620 (The Pile)

Max Activating Token Index: 21

Text #11

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.7206. Min Act: -0.0000

Data Index: 1177723 (The Pile)

Max Activating Token Index: 245

Text #12

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.6504. Min Act: -0.0000

Data Index: 184992 (The Pile)

Max Activating Token Index: 14

Text #13

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.6059. Min Act: -0.0000

Data Index: 1481530 (The Pile)

Max Activating Token Index: 431

Text #14

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.6610. Min Act: -0.0000

Data Index: 1693142 (The Pile)

Max Activating Token Index: 143

Text #15

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.5497. Min Act: -0.0000

Data Index: 1840182 (The Pile)

Max Activating Token Index: 77

Text #16

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.6268. Min Act: -0.0000

Data Index: 323641 (The Pile)

Max Activating Token Index: 151

Text #17

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.5939. Min Act: -0.0000

Data Index: 857388 (The Pile)

Max Activating Token Index: 48

Text #18

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.6303. Min Act: -0.0000

Data Index: 831425 (The Pile)

Max Activating Token Index: 19

Text #19

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.6558. Min Act: -0.0000

Data Index: 1447061 (The Pile)

Max Activating Token Index: 111