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

Dataset: The Pile

Neuron 446 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: 0.6911. Min Range: -0.6911

Max Act: 0.6911. Min Act: -0.0000

Data Index: 1190788 (The Pile)

Max Activating Token Index: 978

Text #1

Max Range: 0.6911. Min Range: -0.6911

Max Act: 0.6131. Min Act: -0.0000

Data Index: 1774321 (The Pile)

Max Activating Token Index: 862

Text #2

Max Range: 0.6911. Min Range: -0.6911

Max Act: 0.6085. Min Act: -0.0000

Data Index: 1880032 (The Pile)

Max Activating Token Index: 938

Text #3

Max Range: 0.6911. Min Range: -0.6911

Max Act: 0.5801. Min Act: -0.0000

Data Index: 1226891 (The Pile)

Max Activating Token Index: 194

Text #4

Max Range: 0.6911. Min Range: -0.6911

Max Act: 0.6498. Min Act: -0.0000

Data Index: 820472 (The Pile)

Max Activating Token Index: 615

Text #5

Max Range: 0.6911. Min Range: -0.6911

Max Act: 0.6015. Min Act: -0.0000

Data Index: 1082000 (The Pile)

Max Activating Token Index: 208

Text #6

Max Range: 0.6911. Min Range: -0.6911

Max Act: 0.6122. Min Act: -0.0000

Data Index: 1772365 (The Pile)

Max Activating Token Index: 251

Text #7

Max Range: 0.6911. Min Range: -0.6911

Max Act: 0.5947. Min Act: -0.0000

Data Index: 1669909 (The Pile)

Max Activating Token Index: 69

Text #8

Max Range: 0.6911. Min Range: -0.6911

Max Act: 0.5945. Min Act: -0.0000

Data Index: 1030334 (The Pile)

Max Activating Token Index: 937

Text #9

Max Range: 0.6911. Min Range: -0.6911

Max Act: 0.5551. Min Act: -0.0000

Data Index: 1294407 (The Pile)

Max Activating Token Index: 269

Text #10

Max Range: 0.6911. Min Range: -0.6911

Max Act: 0.5928. Min Act: -0.0000

Data Index: 1303366 (The Pile)

Max Activating Token Index: 783

Text #11

Max Range: 0.6911. Min Range: -0.6911

Max Act: 0.5552. Min Act: -0.0000

Data Index: 257867 (The Pile)

Max Activating Token Index: 826

Text #12

Max Range: 0.6911. Min Range: -0.6911

Max Act: 0.5847. Min Act: -0.0000

Data Index: 1010252 (The Pile)

Max Activating Token Index: 744

Text #13

Max Range: 0.6911. Min Range: -0.6911

Max Act: 0.5849. Min Act: -0.0000

Data Index: 975813 (The Pile)

Max Activating Token Index: 413

Text #14

Max Range: 0.6911. Min Range: -0.6911

Max Act: 0.5285. Min Act: -0.0000

Data Index: 1625267 (The Pile)

Max Activating Token Index: 886

Text #15

Max Range: 0.6911. Min Range: -0.6911

Max Act: 0.5643. Min Act: -0.0000

Data Index: 292895 (The Pile)

Max Activating Token Index: 953

Text #16

Max Range: 0.6911. Min Range: -0.6911

Max Act: 0.5592. Min Act: -0.0000

Data Index: 563577 (The Pile)

Max Activating Token Index: 172

Text #17

Max Range: 0.6911. Min Range: -0.6911

Max Act: 0.5604. Min Act: -0.0000

Data Index: 1333561 (The Pile)

Max Activating Token Index: 559

Text #18

Max Range: 0.6911. Min Range: -0.6911

Max Act: 0.5724. Min Act: -0.0000

Data Index: 1108248 (The Pile)

Max Activating Token Index: 338

Text #19

Max Range: 0.6911. Min Range: -0.6911

Max Act: 0.5577. Min Act: -0.0000

Data Index: 173431 (The Pile)

Max Activating Token Index: 269