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

Dataset: The Pile

Neuron 1014 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: 0.0780. Min Range: -0.0780

Max Act: 0.0780. Min Act: -0.0000

Data Index: 746231 (The Pile)

Max Activating Token Index: 107

Text #1

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0759. Min Act: -0.0000

Data Index: 723102 (The Pile)

Max Activating Token Index: 274

Text #2

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0702. Min Act: -0.0000

Data Index: 157564 (The Pile)

Max Activating Token Index: 269

Text #3

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0720. Min Act: 0.0000

Data Index: 1985587 (The Pile)

Max Activating Token Index: 117

Text #4

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0694. Min Act: -0.0000

Data Index: 1679113 (The Pile)

Max Activating Token Index: 71

Text #5

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0677. Min Act: -0.0000

Data Index: 1576264 (The Pile)

Max Activating Token Index: 978

Text #6

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0650. Min Act: -0.0000

Data Index: 999935 (The Pile)

Max Activating Token Index: 98

Text #7

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0642. Min Act: -0.0000

Data Index: 865711 (The Pile)

Max Activating Token Index: 166

Text #8

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0636. Min Act: -0.0000

Data Index: 1591116 (The Pile)

Max Activating Token Index: 240

Text #9

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0635. Min Act: -0.0000

Data Index: 1978314 (The Pile)

Max Activating Token Index: 627

Text #10

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0635. Min Act: -0.0000

Data Index: 839557 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0623. Min Act: -0.0000

Data Index: 969833 (The Pile)

Max Activating Token Index: 423

Text #12

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0619. Min Act: -0.0000

Data Index: 945143 (The Pile)

Max Activating Token Index: 118

Text #13

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0619. Min Act: -0.0000

Data Index: 706591 (The Pile)

Max Activating Token Index: 567

Text #14

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0616. Min Act: -0.0000

Data Index: 1131716 (The Pile)

Max Activating Token Index: 132

Text #15

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0616. Min Act: 0.0000

Data Index: 1974224 (The Pile)

Max Activating Token Index: 70

Text #16

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0612. Min Act: -0.0000

Data Index: 1164936 (The Pile)

Max Activating Token Index: 18

Text #17

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0633. Min Act: -0.0000

Data Index: 1808590 (The Pile)

Max Activating Token Index: 172

Text #18

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0611. Min Act: -0.0000

Data Index: 689098 (The Pile)

Max Activating Token Index: 468

Text #19

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0605. Min Act: -0.0000

Data Index: 1387894 (The Pile)

Max Activating Token Index: 41