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

Dataset: The Pile

Neuron 4860 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: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 300701 (The Pile)

Max Activating Token Index: 645

Text #1

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 499614 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 1694665 (The Pile)

Max Activating Token Index: 989

Text #3

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 117666 (The Pile)

Max Activating Token Index: 1003

Text #4

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 364467 (The Pile)

Max Activating Token Index: 1011

Text #5

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 1303455 (The Pile)

Max Activating Token Index: 956

Text #6

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 695669 (The Pile)

Max Activating Token Index: 913

Text #7

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 25324 (The Pile)

Max Activating Token Index: 980

Text #8

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 1613729 (The Pile)

Max Activating Token Index: 998

Text #9

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 1202068 (The Pile)

Max Activating Token Index: 896

Text #10

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 142378 (The Pile)

Max Activating Token Index: 1015

Text #11

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 986316 (The Pile)

Max Activating Token Index: 986

Text #12

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 863530 (The Pile)

Max Activating Token Index: 939

Text #13

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 1346427 (The Pile)

Max Activating Token Index: 1020

Text #14

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 1843637 (The Pile)

Max Activating Token Index: 1011

Text #15

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 1998761 (The Pile)

Max Activating Token Index: 972

Text #16

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 899163 (The Pile)

Max Activating Token Index: 1002

Text #17

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 331 (The Pile)

Max Activating Token Index: 1011

Text #18

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 386102 (The Pile)

Max Activating Token Index: 934

Text #19

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 480579 (The Pile)

Max Activating Token Index: 1020