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

Dataset: The Pile

Neuron 285 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7517. Min Range: -0.7517

Max Act: 0.7411. Min Act: -0.0000

Data Index: 1886427 (The Pile)

Max Activating Token Index: 191

Text #1

Max Range: 0.7517. Min Range: -0.7517

Max Act: 0.7517. Min Act: -0.0000

Data Index: 968338 (The Pile)

Max Activating Token Index: 179

Text #2

Max Range: 0.7517. Min Range: -0.7517

Max Act: 0.6995. Min Act: -0.0000

Data Index: 1635466 (The Pile)

Max Activating Token Index: 826

Text #3

Max Range: 0.7517. Min Range: -0.7517

Max Act: 0.6666. Min Act: -0.0000

Data Index: 1662912 (The Pile)

Max Activating Token Index: 645

Text #4

Max Range: 0.7517. Min Range: -0.7517

Max Act: 0.6678. Min Act: -0.0000

Data Index: 1958029 (The Pile)

Max Activating Token Index: 658

Text #5

Max Range: 0.7517. Min Range: -0.7517

Max Act: 0.6618. Min Act: -0.0000

Data Index: 1823177 (The Pile)

Max Activating Token Index: 6

Text #6

Max Range: 0.7517. Min Range: -0.7517

Max Act: 0.6016. Min Act: -0.0000

Data Index: 314728 (The Pile)

Max Activating Token Index: 790

Text #7

Max Range: 0.7517. Min Range: -0.7517

Max Act: 0.6560. Min Act: -0.0000

Data Index: 1915604 (The Pile)

Max Activating Token Index: 737

Text #8

Max Range: 0.7517. Min Range: -0.7517

Max Act: 0.6342. Min Act: -0.0000

Data Index: 1911281 (The Pile)

Max Activating Token Index: 475

Text #9

Max Range: 0.7517. Min Range: -0.7517

Max Act: 0.5979. Min Act: -0.0000

Data Index: 85709 (The Pile)

Max Activating Token Index: 676

Text #10

Max Range: 0.7517. Min Range: -0.7517

Max Act: 0.6278. Min Act: -0.0000

Data Index: 257151 (The Pile)

Max Activating Token Index: 245

Text #11

Max Range: 0.7517. Min Range: -0.7517

Max Act: 0.5567. Min Act: -0.0000

Data Index: 18436 (The Pile)

Max Activating Token Index: 967

Text #12

Max Range: 0.7517. Min Range: -0.7517

Max Act: 0.6203. Min Act: -0.0000

Data Index: 148586 (The Pile)

Max Activating Token Index: 779

Text #13

Max Range: 0.7517. Min Range: -0.7517

Max Act: 0.6114. Min Act: -0.0000

Data Index: 186941 (The Pile)

Max Activating Token Index: 500

Text #14

Max Range: 0.7517. Min Range: -0.7517

Max Act: 0.5692. Min Act: -0.0000

Data Index: 432873 (The Pile)

Max Activating Token Index: 844

Text #15

Max Range: 0.7517. Min Range: -0.7517

Max Act: 0.5865. Min Act: -0.0000

Data Index: 465501 (The Pile)

Max Activating Token Index: 492

Text #16

Max Range: 0.7517. Min Range: -0.7517

Max Act: 0.6035. Min Act: -0.0000

Data Index: 1548156 (The Pile)

Max Activating Token Index: 962

Text #17

Max Range: 0.7517. Min Range: -0.7517

Max Act: 0.5980. Min Act: -0.0000

Data Index: 1539823 (The Pile)

Max Activating Token Index: 677

Text #18

Max Range: 0.7517. Min Range: -0.7517

Max Act: 0.5549. Min Act: -0.0000

Data Index: 711092 (The Pile)

Max Activating Token Index: 527

Text #19

Max Range: 0.7517. Min Range: -0.7517

Max Act: 0.6068. Min Act: -0.0000

Data Index: 782202 (The Pile)

Max Activating Token Index: 959