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

Dataset: The Pile

Neuron 780 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0496. Min Range: -1.0496

Max Act: 1.0496. Min Act: -0.0000

Data Index: 191100 (The Pile)

Max Activating Token Index: 265

Text #1

Max Range: 1.0496. Min Range: -1.0496

Max Act: 1.0292. Min Act: -0.0000

Data Index: 1523280 (The Pile)

Max Activating Token Index: 461

Text #2

Max Range: 1.0496. Min Range: -1.0496

Max Act: 0.8926. Min Act: -0.0000

Data Index: 1950720 (The Pile)

Max Activating Token Index: 717

Text #3

Max Range: 1.0496. Min Range: -1.0496

Max Act: 0.9263. Min Act: -0.0000

Data Index: 714724 (The Pile)

Max Activating Token Index: 579

Text #4

Max Range: 1.0496. Min Range: -1.0496

Max Act: 0.9359. Min Act: -0.0000

Data Index: 1727258 (The Pile)

Max Activating Token Index: 623

Text #5

Max Range: 1.0496. Min Range: -1.0496

Max Act: 0.9193. Min Act: -0.0000

Data Index: 668535 (The Pile)

Max Activating Token Index: 1020

Text #6

Max Range: 1.0496. Min Range: -1.0496

Max Act: 0.8862. Min Act: -0.0000

Data Index: 1290732 (The Pile)

Max Activating Token Index: 739

Text #7

Max Range: 1.0496. Min Range: -1.0496

Max Act: 0.9128. Min Act: -0.0000

Data Index: 207923 (The Pile)

Max Activating Token Index: 870

Text #8

Max Range: 1.0496. Min Range: -1.0496

Max Act: 0.9091. Min Act: -0.0000

Data Index: 1714623 (The Pile)

Max Activating Token Index: 775

Text #9

Max Range: 1.0496. Min Range: -1.0496

Max Act: 0.8430. Min Act: -0.0000

Data Index: 217664 (The Pile)

Max Activating Token Index: 483

Text #10

Max Range: 1.0496. Min Range: -1.0496

Max Act: 0.8846. Min Act: -0.0000

Data Index: 468488 (The Pile)

Max Activating Token Index: 789

Text #11

Max Range: 1.0496. Min Range: -1.0496

Max Act: 0.9233. Min Act: -0.0000

Data Index: 155276 (The Pile)

Max Activating Token Index: 721

Text #12

Max Range: 1.0496. Min Range: -1.0496

Max Act: 0.8144. Min Act: -0.0000

Data Index: 1665475 (The Pile)

Max Activating Token Index: 593

Text #13

Max Range: 1.0496. Min Range: -1.0496

Max Act: 0.8068. Min Act: -0.0000

Data Index: 1756895 (The Pile)

Max Activating Token Index: 531

Text #14

Max Range: 1.0496. Min Range: -1.0496

Max Act: 0.8560. Min Act: -0.0000

Data Index: 535941 (The Pile)

Max Activating Token Index: 609

Text #15

Max Range: 1.0496. Min Range: -1.0496

Max Act: 0.8452. Min Act: -0.0000

Data Index: 700006 (The Pile)

Max Activating Token Index: 574

Text #16

Max Range: 1.0496. Min Range: -1.0496

Max Act: 0.7616. Min Act: -0.0000

Data Index: 111590 (The Pile)

Max Activating Token Index: 595

Text #17

Max Range: 1.0496. Min Range: -1.0496

Max Act: 0.7891. Min Act: -0.0000

Data Index: 701577 (The Pile)

Max Activating Token Index: 736

Text #18

Max Range: 1.0496. Min Range: -1.0496

Max Act: 0.8620. Min Act: -0.0000

Data Index: 1568171 (The Pile)

Max Activating Token Index: 891

Text #19

Max Range: 1.0496. Min Range: -1.0496

Max Act: 0.8058. Min Act: -0.0000

Data Index: 1891243 (The Pile)

Max Activating Token Index: 757