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

Dataset: The Pile

Neuron 4719 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: 549621 (The Pile)

Max Activating Token Index: 926

Text #1

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0000

Data Index: 70364 (The Pile)

Max Activating Token Index: 1009

Text #2

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0000

Data Index: 1543512 (The Pile)

Max Activating Token Index: 1021

Text #3

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0000

Data Index: 516756 (The Pile)

Max Activating Token Index: 1008

Text #4

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0000

Data Index: 1441666 (The Pile)

Max Activating Token Index: 1005

Text #5

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0000

Data Index: 900825 (The Pile)

Max Activating Token Index: 1000

Text #6

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0000

Data Index: 1382325 (The Pile)

Max Activating Token Index: 982

Text #7

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0000

Data Index: 621915 (The Pile)

Max Activating Token Index: 1004

Text #8

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0000

Data Index: 945432 (The Pile)

Max Activating Token Index: 945

Text #9

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0000

Data Index: 1778265 (The Pile)

Max Activating Token Index: 1011

Text #10

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0000

Data Index: 894801 (The Pile)

Max Activating Token Index: 1013

Text #11

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0000

Data Index: 1911869 (The Pile)

Max Activating Token Index: 1010

Text #12

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0000

Data Index: 1113726 (The Pile)

Max Activating Token Index: 930

Text #13

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0000

Data Index: 1425004 (The Pile)

Max Activating Token Index: 1018

Text #14

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0000

Data Index: 1465343 (The Pile)

Max Activating Token Index: 956

Text #15

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0000

Data Index: 1355412 (The Pile)

Max Activating Token Index: 959

Text #16

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0000

Data Index: 1541361 (The Pile)

Max Activating Token Index: 975

Text #17

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0000

Data Index: 1619627 (The Pile)

Max Activating Token Index: 1006

Text #18

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0000

Data Index: 315869 (The Pile)

Max Activating Token Index: 988

Text #19

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0000

Data Index: 1581050 (The Pile)

Max Activating Token Index: 1005