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

Dataset: The Pile

Neuron 1775 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.7036. Min Act: -0.0000

Data Index: 634354 (The Pile)

Max Activating Token Index: 505

Text #1

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.4869. Min Act: -0.0000

Data Index: 1159176 (The Pile)

Max Activating Token Index: 1006

Text #2

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.3764. Min Act: -0.0000

Data Index: 1420952 (The Pile)

Max Activating Token Index: 34

Text #3

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.4348. Min Act: -0.0000

Data Index: 1460613 (The Pile)

Max Activating Token Index: 291

Text #4

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.3700. Min Act: -0.0000

Data Index: 650313 (The Pile)

Max Activating Token Index: 844

Text #5

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.2308. Min Act: -0.0000

Data Index: 1595552 (The Pile)

Max Activating Token Index: 774

Text #6

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.3937. Min Act: -0.0000

Data Index: 1014014 (The Pile)

Max Activating Token Index: 437

Text #7

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.3694. Min Act: -0.0000

Data Index: 16425 (The Pile)

Max Activating Token Index: 457

Text #8

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.3770. Min Act: -0.0000

Data Index: 19251 (The Pile)

Max Activating Token Index: 621

Text #9

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.3035. Min Act: -0.0000

Data Index: 1634169 (The Pile)

Max Activating Token Index: 645

Text #10

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.1617. Min Act: -0.0000

Data Index: 590624 (The Pile)

Max Activating Token Index: 790

Text #11

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.2285. Min Act: -0.0000

Data Index: 578423 (The Pile)

Max Activating Token Index: 903

Text #12

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.2129. Min Act: -0.0000

Data Index: 30624 (The Pile)

Max Activating Token Index: 633

Text #13

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.1795. Min Act: -0.0000

Data Index: 859966 (The Pile)

Max Activating Token Index: 556

Text #14

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.1978. Min Act: -0.0000

Data Index: 1033710 (The Pile)

Max Activating Token Index: 1003

Text #15

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.2645. Min Act: -0.0000

Data Index: 172122 (The Pile)

Max Activating Token Index: 807

Text #16

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.2322. Min Act: -0.0000

Data Index: 1250794 (The Pile)

Max Activating Token Index: 896

Text #17

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.3285. Min Act: -0.0000

Data Index: 292706 (The Pile)

Max Activating Token Index: 167

Text #18

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.1089. Min Act: -0.0000

Data Index: 374868 (The Pile)

Max Activating Token Index: 593

Text #19

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.0499. Min Act: -0.0000

Data Index: 1720660 (The Pile)

Max Activating Token Index: 671