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

Dataset: The Pile

Neuron 3216 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: 0.7850. Min Range: -0.7850

Max Act: 0.7850. Min Act: -0.0000

Data Index: 1592240 (The Pile)

Max Activating Token Index: 440

Text #1

Max Range: 0.7850. Min Range: -0.7850

Max Act: 0.7661. Min Act: -0.0000

Data Index: 1533094 (The Pile)

Max Activating Token Index: 472

Text #2

Max Range: 0.7850. Min Range: -0.7850

Max Act: 0.5729. Min Act: -0.0000

Data Index: 991805 (The Pile)

Max Activating Token Index: 893

Text #3

Max Range: 0.7850. Min Range: -0.7850

Max Act: 0.6034. Min Act: -0.0000

Data Index: 862584 (The Pile)

Max Activating Token Index: 1011

Text #4

Max Range: 0.7850. Min Range: -0.7850

Max Act: 0.6667. Min Act: -0.0000

Data Index: 861648 (The Pile)

Max Activating Token Index: 40

Text #5

Max Range: 0.7850. Min Range: -0.7850

Max Act: 0.6968. Min Act: -0.0000

Data Index: 915576 (The Pile)

Max Activating Token Index: 776

Text #6

Max Range: 0.7850. Min Range: -0.7850

Max Act: 0.6111. Min Act: -0.0000

Data Index: 1518671 (The Pile)

Max Activating Token Index: 939

Text #7

Max Range: 0.7850. Min Range: -0.7850

Max Act: 0.6310. Min Act: -0.0000

Data Index: 5187 (The Pile)

Max Activating Token Index: 751

Text #8

Max Range: 0.7850. Min Range: -0.7850

Max Act: 0.6543. Min Act: -0.0000

Data Index: 87157 (The Pile)

Max Activating Token Index: 616

Text #9

Max Range: 0.7850. Min Range: -0.7850

Max Act: 0.5629. Min Act: -0.0000

Data Index: 225637 (The Pile)

Max Activating Token Index: 926

Text #10

Max Range: 0.7850. Min Range: -0.7850

Max Act: 0.6214. Min Act: -0.0000

Data Index: 969756 (The Pile)

Max Activating Token Index: 851

Text #11

Max Range: 0.7850. Min Range: -0.7850

Max Act: 0.6436. Min Act: -0.0000

Data Index: 1730611 (The Pile)

Max Activating Token Index: 983

Text #12

Max Range: 0.7850. Min Range: -0.7850

Max Act: 0.5867. Min Act: -0.0000

Data Index: 229526 (The Pile)

Max Activating Token Index: 619

Text #13

Max Range: 0.7850. Min Range: -0.7850

Max Act: 0.6297. Min Act: -0.0000

Data Index: 1433645 (The Pile)

Max Activating Token Index: 207

Text #14

Max Range: 0.7850. Min Range: -0.7850

Max Act: 0.6087. Min Act: -0.0000

Data Index: 1837737 (The Pile)

Max Activating Token Index: 626

Text #15

Max Range: 0.7850. Min Range: -0.7850

Max Act: 0.6143. Min Act: -0.0000

Data Index: 1992975 (The Pile)

Max Activating Token Index: 677

Text #16

Max Range: 0.7850. Min Range: -0.7850

Max Act: 0.5888. Min Act: -0.0000

Data Index: 67904 (The Pile)

Max Activating Token Index: 255

Text #17

Max Range: 0.7850. Min Range: -0.7850

Max Act: 0.5546. Min Act: -0.0000

Data Index: 1068149 (The Pile)

Max Activating Token Index: 66

Text #18

Max Range: 0.7850. Min Range: -0.7850

Max Act: 0.5362. Min Act: -0.0000

Data Index: 317529 (The Pile)

Max Activating Token Index: 793

Text #19

Max Range: 0.7850. Min Range: -0.7850

Max Act: 0.5858. Min Act: -0.0000

Data Index: 816898 (The Pile)

Max Activating Token Index: 867