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

Dataset: The Pile

Neuron 963 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: 1.5864. Min Range: -1.5864

Max Act: 1.5864. Min Act: -0.0000

Data Index: 1100769 (The Pile)

Max Activating Token Index: 790

Text #1

Max Range: 1.5864. Min Range: -1.5864

Max Act: 1.4716. Min Act: -0.0000

Data Index: 199234 (The Pile)

Max Activating Token Index: 376

Text #2

Max Range: 1.5864. Min Range: -1.5864

Max Act: 1.3809. Min Act: -0.0000

Data Index: 1748041 (The Pile)

Max Activating Token Index: 453

Text #3

Max Range: 1.5864. Min Range: -1.5864

Max Act: 1.3810. Min Act: -0.0000

Data Index: 1846575 (The Pile)

Max Activating Token Index: 617

Text #4

Max Range: 1.5864. Min Range: -1.5864

Max Act: 1.4204. Min Act: -0.0000

Data Index: 467867 (The Pile)

Max Activating Token Index: 742

Text #5

Max Range: 1.5864. Min Range: -1.5864

Max Act: 1.4481. Min Act: -0.0000

Data Index: 518493 (The Pile)

Max Activating Token Index: 753

Text #6

Max Range: 1.5864. Min Range: -1.5864

Max Act: 1.4737. Min Act: -0.0000

Data Index: 1664710 (The Pile)

Max Activating Token Index: 1004

Text #7

Max Range: 1.5864. Min Range: -1.5864

Max Act: 1.5008. Min Act: -0.0000

Data Index: 1084866 (The Pile)

Max Activating Token Index: 589

Text #8

Max Range: 1.5864. Min Range: -1.5864

Max Act: 1.4073. Min Act: -0.0000

Data Index: 771761 (The Pile)

Max Activating Token Index: 33

Text #9

Max Range: 1.5864. Min Range: -1.5864

Max Act: 1.3300. Min Act: -0.0000

Data Index: 1542484 (The Pile)

Max Activating Token Index: 372

Text #10

Max Range: 1.5864. Min Range: -1.5864

Max Act: 1.2467. Min Act: -0.0000

Data Index: 1261492 (The Pile)

Max Activating Token Index: 725

Text #11

Max Range: 1.5864. Min Range: -1.5864

Max Act: 1.3898. Min Act: -0.0000

Data Index: 1739740 (The Pile)

Max Activating Token Index: 867

Text #12

Max Range: 1.5864. Min Range: -1.5864

Max Act: 1.4725. Min Act: -0.0000

Data Index: 816625 (The Pile)

Max Activating Token Index: 494

Text #13

Max Range: 1.5864. Min Range: -1.5864

Max Act: 1.2925. Min Act: -0.0000

Data Index: 745225 (The Pile)

Max Activating Token Index: 357

Text #14

Max Range: 1.5864. Min Range: -1.5864

Max Act: 1.0415. Min Act: -0.0000

Data Index: 1003377 (The Pile)

Max Activating Token Index: 948

Text #15

Max Range: 1.5864. Min Range: -1.5864

Max Act: 1.3941. Min Act: -0.0000

Data Index: 1015038 (The Pile)

Max Activating Token Index: 977

Text #16

Max Range: 1.5864. Min Range: -1.5864

Max Act: 1.3491. Min Act: -0.0000

Data Index: 130689 (The Pile)

Max Activating Token Index: 622

Text #17

Max Range: 1.5864. Min Range: -1.5864

Max Act: 1.4156. Min Act: -0.0000

Data Index: 1500502 (The Pile)

Max Activating Token Index: 173

Text #18

Max Range: 1.5864. Min Range: -1.5864

Max Act: 1.0585. Min Act: -0.0000

Data Index: 84393 (The Pile)

Max Activating Token Index: 1002

Text #19

Max Range: 1.5864. Min Range: -1.5864

Max Act: 1.3203. Min Act: -0.0000

Data Index: 1057466 (The Pile)

Max Activating Token Index: 210