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

Dataset: The Pile

Neuron 1584 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.0950. Min Range: -7.0950

Max Act: 7.0950. Min Act: -0.0000

Data Index: 803105 (The Pile)

Max Activating Token Index: 449

Text #1

Max Range: 7.0950. Min Range: -7.0950

Max Act: 6.5463. Min Act: -0.0000

Data Index: 1844861 (The Pile)

Max Activating Token Index: 663

Text #2

Max Range: 7.0950. Min Range: -7.0950

Max Act: 6.1144. Min Act: -0.0000

Data Index: 172367 (The Pile)

Max Activating Token Index: 855

Text #3

Max Range: 7.0950. Min Range: -7.0950

Max Act: 5.8395. Min Act: -0.0000

Data Index: 943122 (The Pile)

Max Activating Token Index: 927

Text #4

Max Range: 7.0950. Min Range: -7.0950

Max Act: 6.1832. Min Act: -0.0000

Data Index: 911690 (The Pile)

Max Activating Token Index: 1009

Text #5

Max Range: 7.0950. Min Range: -7.0950

Max Act: 5.9504. Min Act: -0.0000

Data Index: 1405708 (The Pile)

Max Activating Token Index: 979

Text #6

Max Range: 7.0950. Min Range: -7.0950

Max Act: 5.6294. Min Act: -0.0000

Data Index: 907763 (The Pile)

Max Activating Token Index: 624

Text #7

Max Range: 7.0950. Min Range: -7.0950

Max Act: 5.6086. Min Act: -0.0000

Data Index: 1791224 (The Pile)

Max Activating Token Index: 869

Text #8

Max Range: 7.0950. Min Range: -7.0950

Max Act: 5.5583. Min Act: -0.0000

Data Index: 1567 (The Pile)

Max Activating Token Index: 794

Text #9

Max Range: 7.0950. Min Range: -7.0950

Max Act: 5.5039. Min Act: -0.0000

Data Index: 1936193 (The Pile)

Max Activating Token Index: 810

Text #10

Max Range: 7.0950. Min Range: -7.0950

Max Act: 5.3659. Min Act: -0.0000

Data Index: 1977412 (The Pile)

Max Activating Token Index: 596

Text #11

Max Range: 7.0950. Min Range: -7.0950

Max Act: 5.0937. Min Act: -0.0000

Data Index: 567052 (The Pile)

Max Activating Token Index: 698

Text #12

Max Range: 7.0950. Min Range: -7.0950

Max Act: 5.1709. Min Act: -0.0000

Data Index: 860882 (The Pile)

Max Activating Token Index: 840

Text #13

Max Range: 7.0950. Min Range: -7.0950

Max Act: 5.3606. Min Act: -0.0000

Data Index: 363342 (The Pile)

Max Activating Token Index: 308

Text #14

Max Range: 7.0950. Min Range: -7.0950

Max Act: 5.3744. Min Act: -0.0000

Data Index: 830706 (The Pile)

Max Activating Token Index: 609

Text #15

Max Range: 7.0950. Min Range: -7.0950

Max Act: 5.5297. Min Act: -0.0000

Data Index: 1525421 (The Pile)

Max Activating Token Index: 950

Text #16

Max Range: 7.0950. Min Range: -7.0950

Max Act: 4.9289. Min Act: -0.0000

Data Index: 591392 (The Pile)

Max Activating Token Index: 987

Text #17

Max Range: 7.0950. Min Range: -7.0950

Max Act: 5.3068. Min Act: -0.0000

Data Index: 213584 (The Pile)

Max Activating Token Index: 754

Text #18

Max Range: 7.0950. Min Range: -7.0950

Max Act: 5.4821. Min Act: -0.0000

Data Index: 1416149 (The Pile)

Max Activating Token Index: 308

Text #19

Max Range: 7.0950. Min Range: -7.0950

Max Act: 5.2336. Min Act: -0.0000

Data Index: 535014 (The Pile)

Max Activating Token Index: 774