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

Dataset: The Pile

Neuron 1743 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.1026. Min Range: -1.1026

Max Act: 1.1026. Min Act: -0.0000

Data Index: 1605724 (The Pile)

Max Activating Token Index: 361

Text #1

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.9117. Min Act: -0.0000

Data Index: 793934 (The Pile)

Max Activating Token Index: 790

Text #2

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.8645. Min Act: -0.0000

Data Index: 1787287 (The Pile)

Max Activating Token Index: 642

Text #3

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.7760. Min Act: -0.0000

Data Index: 155277 (The Pile)

Max Activating Token Index: 217

Text #4

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.7053. Min Act: -0.0000

Data Index: 1330324 (The Pile)

Max Activating Token Index: 100

Text #5

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.6895. Min Act: -0.0000

Data Index: 4821 (The Pile)

Max Activating Token Index: 288

Text #6

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.6618. Min Act: -0.0000

Data Index: 811215 (The Pile)

Max Activating Token Index: 890

Text #7

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.6611. Min Act: -0.0000

Data Index: 340828 (The Pile)

Max Activating Token Index: 1014

Text #8

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.6610. Min Act: -0.0000

Data Index: 1864146 (The Pile)

Max Activating Token Index: 303

Text #9

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.5944. Min Act: -0.0000

Data Index: 146013 (The Pile)

Max Activating Token Index: 998

Text #10

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.5655. Min Act: -0.0000

Data Index: 422664 (The Pile)

Max Activating Token Index: 980

Text #11

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.5946. Min Act: -0.0000

Data Index: 274745 (The Pile)

Max Activating Token Index: 120

Text #12

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.5573. Min Act: -0.0000

Data Index: 839501 (The Pile)

Max Activating Token Index: 32

Text #13

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.5561. Min Act: -0.0000

Data Index: 565476 (The Pile)

Max Activating Token Index: 684

Text #14

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.5677. Min Act: -0.0000

Data Index: 1866714 (The Pile)

Max Activating Token Index: 229

Text #15

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.5468. Min Act: -0.0000

Data Index: 1597212 (The Pile)

Max Activating Token Index: 341

Text #16

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.5611. Min Act: -0.0000

Data Index: 1436571 (The Pile)

Max Activating Token Index: 138

Text #17

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.5226. Min Act: -0.0000

Data Index: 1436654 (The Pile)

Max Activating Token Index: 973

Text #18

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.5212. Min Act: -0.0000

Data Index: 1685422 (The Pile)

Max Activating Token Index: 123

Text #19

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.5304. Min Act: -0.0000

Data Index: 1749721 (The Pile)

Max Activating Token Index: 574