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

Dataset: The Pile

Neuron 863 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: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0000

Data Index: 1435898 (The Pile)

Max Activating Token Index: 24

Text #1

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0000

Data Index: 1389669 (The Pile)

Max Activating Token Index: 114

Text #2

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0000

Data Index: 140048 (The Pile)

Max Activating Token Index: 225

Text #3

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0000

Data Index: 1061096 (The Pile)

Max Activating Token Index: 752

Text #4

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0000

Data Index: 995298 (The Pile)

Max Activating Token Index: 811

Text #5

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0000

Data Index: 1302602 (The Pile)

Max Activating Token Index: 963

Text #6

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0000

Data Index: 1031698 (The Pile)

Max Activating Token Index: 958

Text #7

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0000

Data Index: 27192 (The Pile)

Max Activating Token Index: 16

Text #8

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0000

Data Index: 1805144 (The Pile)

Max Activating Token Index: 28

Text #9

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0000

Data Index: 1417872 (The Pile)

Max Activating Token Index: 862

Text #10

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0000

Data Index: 478095 (The Pile)

Max Activating Token Index: 983

Text #11

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0000

Data Index: 72388 (The Pile)

Max Activating Token Index: 983

Text #12

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0000

Data Index: 1787066 (The Pile)

Max Activating Token Index: 15

Text #13

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0000

Data Index: 561437 (The Pile)

Max Activating Token Index: 973

Text #14

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0000

Data Index: 849323 (The Pile)

Max Activating Token Index: 982

Text #15

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0000

Data Index: 816593 (The Pile)

Max Activating Token Index: 141

Text #16

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0000

Data Index: 1622712 (The Pile)

Max Activating Token Index: 1012

Text #17

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0000

Data Index: 429979 (The Pile)

Max Activating Token Index: 960

Text #18

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0000

Data Index: 804287 (The Pile)

Max Activating Token Index: 952

Text #19

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0000

Data Index: 605954 (The Pile)

Max Activating Token Index: 164