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

Dataset: The Pile

Neuron 1546 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9097. Min Range: -0.9097

Max Act: 0.9097. Min Act: -0.0000

Data Index: 1944513 (The Pile)

Max Activating Token Index: 935

Text #1

Max Range: 0.9097. Min Range: -0.9097

Max Act: 0.7538. Min Act: -0.0000

Data Index: 1446483 (The Pile)

Max Activating Token Index: 952

Text #2

Max Range: 0.9097. Min Range: -0.9097

Max Act: 0.7971. Min Act: -0.0000

Data Index: 1608900 (The Pile)

Max Activating Token Index: 580

Text #3

Max Range: 0.9097. Min Range: -0.9097

Max Act: 0.8055. Min Act: -0.0000

Data Index: 439248 (The Pile)

Max Activating Token Index: 956

Text #4

Max Range: 0.9097. Min Range: -0.9097

Max Act: 0.6934. Min Act: -0.0000

Data Index: 823689 (The Pile)

Max Activating Token Index: 1011

Text #5

Max Range: 0.9097. Min Range: -0.9097

Max Act: 0.7437. Min Act: -0.0000

Data Index: 887233 (The Pile)

Max Activating Token Index: 626

Text #6

Max Range: 0.9097. Min Range: -0.9097

Max Act: 0.7442. Min Act: -0.0000

Data Index: 1819540 (The Pile)

Max Activating Token Index: 995

Text #7

Max Range: 0.9097. Min Range: -0.9097

Max Act: 0.6831. Min Act: 0.0000

Data Index: 611757 (The Pile)

Max Activating Token Index: 336

Text #8

Max Range: 0.9097. Min Range: -0.9097

Max Act: 0.7214. Min Act: 0.0000

Data Index: 664225 (The Pile)

Max Activating Token Index: 124

Text #9

Max Range: 0.9097. Min Range: -0.9097

Max Act: 0.6795. Min Act: -0.0000

Data Index: 1670194 (The Pile)

Max Activating Token Index: 666

Text #10

Max Range: 0.9097. Min Range: -0.9097

Max Act: 0.7124. Min Act: -0.0000

Data Index: 691225 (The Pile)

Max Activating Token Index: 963

Text #11

Max Range: 0.9097. Min Range: -0.9097

Max Act: 0.6747. Min Act: -0.0000

Data Index: 889215 (The Pile)

Max Activating Token Index: 422

Text #12

Max Range: 0.9097. Min Range: -0.9097

Max Act: 0.6646. Min Act: 0.0000

Data Index: 130654 (The Pile)

Max Activating Token Index: 734

Text #13

Max Range: 0.9097. Min Range: -0.9097

Max Act: 0.6423. Min Act: 0.0000

Data Index: 214646 (The Pile)

Max Activating Token Index: 327

Text #14

Max Range: 0.9097. Min Range: -0.9097

Max Act: 0.6631. Min Act: -0.0000

Data Index: 1232945 (The Pile)

Max Activating Token Index: 701

Text #15

Max Range: 0.9097. Min Range: -0.9097

Max Act: 0.6616. Min Act: -0.0000

Data Index: 1453445 (The Pile)

Max Activating Token Index: 485

Text #16

Max Range: 0.9097. Min Range: -0.9097

Max Act: 0.6486. Min Act: -0.0000

Data Index: 1350814 (The Pile)

Max Activating Token Index: 654

Text #17

Max Range: 0.9097. Min Range: -0.9097

Max Act: 0.6486. Min Act: 0.0001

Data Index: 1882277 (The Pile)

Max Activating Token Index: 417

Text #18

Max Range: 0.9097. Min Range: -0.9097

Max Act: 0.6479. Min Act: -0.0000

Data Index: 430412 (The Pile)

Max Activating Token Index: 119

Text #19

Max Range: 0.9097. Min Range: -0.9097

Max Act: 0.6370. Min Act: 0.0000

Data Index: 1309105 (The Pile)

Max Activating Token Index: 414