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

Dataset: The Pile

Neuron 4926 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: 8.6744. Min Range: -8.6744

Max Act: 8.5819. Min Act: -0.0000

Data Index: 1273743 (The Pile)

Max Activating Token Index: 291

Text #1

Max Range: 8.6744. Min Range: -8.6744

Max Act: 8.0561. Min Act: -0.0000

Data Index: 1969046 (The Pile)

Max Activating Token Index: 380

Text #2

Max Range: 8.6744. Min Range: -8.6744

Max Act: 7.7583. Min Act: -0.0000

Data Index: 1131123 (The Pile)

Max Activating Token Index: 478

Text #3

Max Range: 8.6744. Min Range: -8.6744

Max Act: 7.8995. Min Act: -0.0000

Data Index: 1759073 (The Pile)

Max Activating Token Index: 49

Text #4

Max Range: 8.6744. Min Range: -8.6744

Max Act: 8.6744. Min Act: -0.0000

Data Index: 1321902 (The Pile)

Max Activating Token Index: 264

Text #5

Max Range: 8.6744. Min Range: -8.6744

Max Act: 7.9709. Min Act: -0.0000

Data Index: 773368 (The Pile)

Max Activating Token Index: 138

Text #6

Max Range: 8.6744. Min Range: -8.6744

Max Act: 7.9170. Min Act: -0.0000

Data Index: 1512456 (The Pile)

Max Activating Token Index: 206

Text #7

Max Range: 8.6744. Min Range: -8.6744

Max Act: 7.5469. Min Act: -0.0000

Data Index: 1035459 (The Pile)

Max Activating Token Index: 547

Text #8

Max Range: 8.6744. Min Range: -8.6744

Max Act: 6.9882. Min Act: -0.0000

Data Index: 367468 (The Pile)

Max Activating Token Index: 378

Text #9

Max Range: 8.6744. Min Range: -8.6744

Max Act: 7.5643. Min Act: -0.0000

Data Index: 1557647 (The Pile)

Max Activating Token Index: 88

Text #10

Max Range: 8.6744. Min Range: -8.6744

Max Act: 7.1620. Min Act: -0.0000

Data Index: 1955287 (The Pile)

Max Activating Token Index: 615

Text #11

Max Range: 8.6744. Min Range: -8.6744

Max Act: 7.1875. Min Act: -0.0000

Data Index: 1703635 (The Pile)

Max Activating Token Index: 722

Text #12

Max Range: 8.6744. Min Range: -8.6744

Max Act: 7.1534. Min Act: -0.0000

Data Index: 1044886 (The Pile)

Max Activating Token Index: 218

Text #13

Max Range: 8.6744. Min Range: -8.6744

Max Act: 7.3161. Min Act: -0.0000

Data Index: 662765 (The Pile)

Max Activating Token Index: 770

Text #14

Max Range: 8.6744. Min Range: -8.6744

Max Act: 7.2203. Min Act: -0.0000

Data Index: 261798 (The Pile)

Max Activating Token Index: 585

Text #15

Max Range: 8.6744. Min Range: -8.6744

Max Act: 6.6215. Min Act: -0.0000

Data Index: 1898511 (The Pile)

Max Activating Token Index: 56

Text #16

Max Range: 8.6744. Min Range: -8.6744

Max Act: 6.7863. Min Act: -0.0000

Data Index: 1882330 (The Pile)

Max Activating Token Index: 340

Text #17

Max Range: 8.6744. Min Range: -8.6744

Max Act: 6.8024. Min Act: -0.0000

Data Index: 346540 (The Pile)

Max Activating Token Index: 119

Text #18

Max Range: 8.6744. Min Range: -8.6744

Max Act: 7.4069. Min Act: -0.0000

Data Index: 1340022 (The Pile)

Max Activating Token Index: 583

Text #19

Max Range: 8.6744. Min Range: -8.6744

Max Act: 6.6595. Min Act: -0.0000

Data Index: 999165 (The Pile)

Max Activating Token Index: 40