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

Dataset: The Pile

Neuron 3922 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: 1.3804. Min Range: -1.3804

Max Act: 1.3804. Min Act: -0.0000

Data Index: 372211 (The Pile)

Max Activating Token Index: 274

Text #1

Max Range: 1.3804. Min Range: -1.3804

Max Act: 1.3166. Min Act: -0.0000

Data Index: 584230 (The Pile)

Max Activating Token Index: 630

Text #2

Max Range: 1.3804. Min Range: -1.3804

Max Act: 1.2436. Min Act: -0.0000

Data Index: 1219886 (The Pile)

Max Activating Token Index: 488

Text #3

Max Range: 1.3804. Min Range: -1.3804

Max Act: 1.1456. Min Act: -0.0000

Data Index: 467491 (The Pile)

Max Activating Token Index: 354

Text #4

Max Range: 1.3804. Min Range: -1.3804

Max Act: 0.9773. Min Act: -0.0000

Data Index: 424128 (The Pile)

Max Activating Token Index: 452

Text #5

Max Range: 1.3804. Min Range: -1.3804

Max Act: 0.9371. Min Act: -0.0000

Data Index: 145506 (The Pile)

Max Activating Token Index: 50

Text #6

Max Range: 1.3804. Min Range: -1.3804

Max Act: 0.8193. Min Act: -0.0000

Data Index: 1456057 (The Pile)

Max Activating Token Index: 27

Text #7

Max Range: 1.3804. Min Range: -1.3804

Max Act: 0.9437. Min Act: -0.0000

Data Index: 1969922 (The Pile)

Max Activating Token Index: 672

Text #8

Max Range: 1.3804. Min Range: -1.3804

Max Act: 0.8826. Min Act: -0.0000

Data Index: 1839378 (The Pile)

Max Activating Token Index: 193

Text #9

Max Range: 1.3804. Min Range: -1.3804

Max Act: 0.9021. Min Act: -0.0000

Data Index: 1796104 (The Pile)

Max Activating Token Index: 834

Text #10

Max Range: 1.3804. Min Range: -1.3804

Max Act: 0.8065. Min Act: -0.0000

Data Index: 760325 (The Pile)

Max Activating Token Index: 35

Text #11

Max Range: 1.3804. Min Range: -1.3804

Max Act: 0.8733. Min Act: -0.0000

Data Index: 1068082 (The Pile)

Max Activating Token Index: 673

Text #12

Max Range: 1.3804. Min Range: -1.3804

Max Act: 0.7546. Min Act: -0.0000

Data Index: 1536713 (The Pile)

Max Activating Token Index: 971

Text #13

Max Range: 1.3804. Min Range: -1.3804

Max Act: 0.7629. Min Act: -0.0000

Data Index: 849018 (The Pile)

Max Activating Token Index: 666

Text #14

Max Range: 1.3804. Min Range: -1.3804

Max Act: 0.8459. Min Act: -0.0000

Data Index: 1469900 (The Pile)

Max Activating Token Index: 696

Text #15

Max Range: 1.3804. Min Range: -1.3804

Max Act: 0.7623. Min Act: -0.0000

Data Index: 1718962 (The Pile)

Max Activating Token Index: 780

Text #16

Max Range: 1.3804. Min Range: -1.3804

Max Act: 0.7820. Min Act: -0.0000

Data Index: 1238134 (The Pile)

Max Activating Token Index: 73

Text #17

Max Range: 1.3804. Min Range: -1.3804

Max Act: 0.8537. Min Act: -0.0000

Data Index: 1655623 (The Pile)

Max Activating Token Index: 89

Text #18

Max Range: 1.3804. Min Range: -1.3804

Max Act: 0.7258. Min Act: -0.0000

Data Index: 122462 (The Pile)

Max Activating Token Index: 423

Text #19

Max Range: 1.3804. Min Range: -1.3804

Max Act: 0.7616. Min Act: -0.0000

Data Index: 126019 (The Pile)

Max Activating Token Index: 267