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

Dataset: The Pile

Neuron 2658 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7273. Min Range: -3.7273

Max Act: 3.7273. Min Act: -0.0000

Data Index: 1851954 (The Pile)

Max Activating Token Index: 39

Text #1

Max Range: 3.7273. Min Range: -3.7273

Max Act: 3.5677. Min Act: -0.0000

Data Index: 497353 (The Pile)

Max Activating Token Index: 41

Text #2

Max Range: 3.7273. Min Range: -3.7273

Max Act: 3.3233. Min Act: -0.0000

Data Index: 1557329 (The Pile)

Max Activating Token Index: 977

Text #3

Max Range: 3.7273. Min Range: -3.7273

Max Act: 3.1310. Min Act: -0.0000

Data Index: 183749 (The Pile)

Max Activating Token Index: 598

Text #4

Max Range: 3.7273. Min Range: -3.7273

Max Act: 3.1923. Min Act: -0.0000

Data Index: 1757910 (The Pile)

Max Activating Token Index: 494

Text #5

Max Range: 3.7273. Min Range: -3.7273

Max Act: 3.3756. Min Act: -0.0000

Data Index: 1668122 (The Pile)

Max Activating Token Index: 596

Text #6

Max Range: 3.7273. Min Range: -3.7273

Max Act: 3.0988. Min Act: -0.0000

Data Index: 734568 (The Pile)

Max Activating Token Index: 802

Text #7

Max Range: 3.7273. Min Range: -3.7273

Max Act: 3.2288. Min Act: -0.0000

Data Index: 500868 (The Pile)

Max Activating Token Index: 47

Text #8

Max Range: 3.7273. Min Range: -3.7273

Max Act: 2.7471. Min Act: -0.0000

Data Index: 867481 (The Pile)

Max Activating Token Index: 662

Text #9

Max Range: 3.7273. Min Range: -3.7273

Max Act: 3.0800. Min Act: -0.0000

Data Index: 539562 (The Pile)

Max Activating Token Index: 966

Text #10

Max Range: 3.7273. Min Range: -3.7273

Max Act: 3.1295. Min Act: -0.0000

Data Index: 737285 (The Pile)

Max Activating Token Index: 98

Text #11

Max Range: 3.7273. Min Range: -3.7273

Max Act: 2.7034. Min Act: -0.0000

Data Index: 1514123 (The Pile)

Max Activating Token Index: 988

Text #12

Max Range: 3.7273. Min Range: -3.7273

Max Act: 2.8224. Min Act: -0.0000

Data Index: 283065 (The Pile)

Max Activating Token Index: 841

Text #13

Max Range: 3.7273. Min Range: -3.7273

Max Act: 3.3658. Min Act: -0.0000

Data Index: 404110 (The Pile)

Max Activating Token Index: 991

Text #14

Max Range: 3.7273. Min Range: -3.7273

Max Act: 3.0955. Min Act: -0.0000

Data Index: 229881 (The Pile)

Max Activating Token Index: 68

Text #15

Max Range: 3.7273. Min Range: -3.7273

Max Act: 2.9418. Min Act: -0.0000

Data Index: 426618 (The Pile)

Max Activating Token Index: 531

Text #16

Max Range: 3.7273. Min Range: -3.7273

Max Act: 2.8034. Min Act: -0.0000

Data Index: 1885563 (The Pile)

Max Activating Token Index: 967

Text #17

Max Range: 3.7273. Min Range: -3.7273

Max Act: 3.3657. Min Act: -0.0000

Data Index: 1670377 (The Pile)

Max Activating Token Index: 825

Text #18

Max Range: 3.7273. Min Range: -3.7273

Max Act: 3.0642. Min Act: -0.0000

Data Index: 1888834 (The Pile)

Max Activating Token Index: 931

Text #19

Max Range: 3.7273. Min Range: -3.7273

Max Act: 3.0313. Min Act: -0.0000

Data Index: 60719 (The Pile)

Max Activating Token Index: 994