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

Dataset: The Pile

Neuron 3194 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.9041. Min Act: -0.0000

Data Index: 196649 (The Pile)

Max Activating Token Index: 906

Text #1

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.8983. Min Act: -0.0000

Data Index: 1547591 (The Pile)

Max Activating Token Index: 605

Text #2

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.8213. Min Act: -0.0000

Data Index: 481737 (The Pile)

Max Activating Token Index: 363

Text #3

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.8073. Min Act: -0.0000

Data Index: 1851200 (The Pile)

Max Activating Token Index: 806

Text #4

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.7751. Min Act: -0.0000

Data Index: 1416312 (The Pile)

Max Activating Token Index: 378

Text #5

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.7608. Min Act: -0.0000

Data Index: 1001049 (The Pile)

Max Activating Token Index: 717

Text #6

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.6581. Min Act: -0.0000

Data Index: 1868691 (The Pile)

Max Activating Token Index: 670

Text #7

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.7109. Min Act: -0.0000

Data Index: 401545 (The Pile)

Max Activating Token Index: 935

Text #8

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.6521. Min Act: -0.0000

Data Index: 256791 (The Pile)

Max Activating Token Index: 974

Text #9

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.6865. Min Act: -0.0000

Data Index: 1123678 (The Pile)

Max Activating Token Index: 970

Text #10

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.6525. Min Act: -0.0000

Data Index: 1032382 (The Pile)

Max Activating Token Index: 962

Text #11

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.7114. Min Act: -0.0000

Data Index: 712743 (The Pile)

Max Activating Token Index: 679

Text #12

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.6679. Min Act: -0.0000

Data Index: 1954114 (The Pile)

Max Activating Token Index: 672

Text #13

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.5532. Min Act: -0.0000

Data Index: 1253482 (The Pile)

Max Activating Token Index: 178

Text #14

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.5443. Min Act: -0.0000

Data Index: 642927 (The Pile)

Max Activating Token Index: 46

Text #15

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.5212. Min Act: -0.0000

Data Index: 1568504 (The Pile)

Max Activating Token Index: 57

Text #16

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.4800. Min Act: -0.0000

Data Index: 569994 (The Pile)

Max Activating Token Index: 607

Text #17

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.4777. Min Act: -0.0000

Data Index: 354319 (The Pile)

Max Activating Token Index: 976

Text #18

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.4799. Min Act: -0.0000

Data Index: 601867 (The Pile)

Max Activating Token Index: 751

Text #19

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.4607. Min Act: -0.0000

Data Index: 125406 (The Pile)

Max Activating Token Index: 637