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

Dataset: The Pile

Neuron 4493 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.9443. Min Act: -0.0000

Data Index: 1316990 (The Pile)

Max Activating Token Index: 341

Text #1

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.9805. Min Act: -0.0000

Data Index: 1729781 (The Pile)

Max Activating Token Index: 242

Text #2

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.8852. Min Act: -0.0000

Data Index: 38354 (The Pile)

Max Activating Token Index: 665

Text #3

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.9068. Min Act: -0.0000

Data Index: 1298143 (The Pile)

Max Activating Token Index: 1009

Text #4

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.8705. Min Act: -0.0000

Data Index: 1816681 (The Pile)

Max Activating Token Index: 687

Text #5

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.8111. Min Act: -0.0000

Data Index: 929162 (The Pile)

Max Activating Token Index: 758

Text #6

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.8599. Min Act: -0.0000

Data Index: 1699757 (The Pile)

Max Activating Token Index: 762

Text #7

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.7357. Min Act: -0.0000

Data Index: 309069 (The Pile)

Max Activating Token Index: 575

Text #8

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.8818. Min Act: -0.0000

Data Index: 946125 (The Pile)

Max Activating Token Index: 911

Text #9

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.7814. Min Act: -0.0000

Data Index: 1377734 (The Pile)

Max Activating Token Index: 466

Text #10

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.7190. Min Act: -0.0000

Data Index: 432550 (The Pile)

Max Activating Token Index: 816

Text #11

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.7569. Min Act: -0.0000

Data Index: 1681449 (The Pile)

Max Activating Token Index: 387

Text #12

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.7562. Min Act: -0.0000

Data Index: 655071 (The Pile)

Max Activating Token Index: 719

Text #13

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.7481. Min Act: -0.0000

Data Index: 28882 (The Pile)

Max Activating Token Index: 279

Text #14

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.7074. Min Act: -0.0000

Data Index: 542392 (The Pile)

Max Activating Token Index: 945

Text #15

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.7925. Min Act: -0.0000

Data Index: 504189 (The Pile)

Max Activating Token Index: 942

Text #16

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.7841. Min Act: -0.0000

Data Index: 739701 (The Pile)

Max Activating Token Index: 816

Text #17

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.7236. Min Act: -0.0000

Data Index: 265983 (The Pile)

Max Activating Token Index: 432

Text #18

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.7228. Min Act: -0.0000

Data Index: 1370611 (The Pile)

Max Activating Token Index: 350

Text #19

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.6825. Min Act: -0.0000

Data Index: 945631 (The Pile)

Max Activating Token Index: 730