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

Dataset: The Pile

Neuron 1055 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.7459. Min Act: -0.0000

Data Index: 1983507 (The Pile)

Max Activating Token Index: 790

Text #1

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.7703. Min Act: -0.0000

Data Index: 591193 (The Pile)

Max Activating Token Index: 364

Text #2

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.5822. Min Act: -0.0000

Data Index: 1360772 (The Pile)

Max Activating Token Index: 913

Text #3

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.6085. Min Act: -0.0000

Data Index: 1041280 (The Pile)

Max Activating Token Index: 840

Text #4

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.5744. Min Act: -0.0000

Data Index: 1769595 (The Pile)

Max Activating Token Index: 769

Text #5

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.6022. Min Act: -0.0000

Data Index: 1753348 (The Pile)

Max Activating Token Index: 618

Text #6

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.5752. Min Act: -0.0000

Data Index: 1275212 (The Pile)

Max Activating Token Index: 989

Text #7

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.5792. Min Act: -0.0000

Data Index: 1734250 (The Pile)

Max Activating Token Index: 205

Text #8

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.5678. Min Act: -0.0000

Data Index: 1421748 (The Pile)

Max Activating Token Index: 908

Text #9

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.5842. Min Act: -0.0000

Data Index: 546916 (The Pile)

Max Activating Token Index: 247

Text #10

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.6153. Min Act: -0.0000

Data Index: 1738796 (The Pile)

Max Activating Token Index: 530

Text #11

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.4784. Min Act: -0.0000

Data Index: 418995 (The Pile)

Max Activating Token Index: 944

Text #12

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.5400. Min Act: -0.0000

Data Index: 12023 (The Pile)

Max Activating Token Index: 733

Text #13

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.5186. Min Act: -0.0000

Data Index: 1784830 (The Pile)

Max Activating Token Index: 276

Text #14

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.5363. Min Act: -0.0000

Data Index: 1366936 (The Pile)

Max Activating Token Index: 697

Text #15

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.5877. Min Act: -0.0000

Data Index: 1607094 (The Pile)

Max Activating Token Index: 585

Text #16

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.5774. Min Act: -0.0000

Data Index: 620907 (The Pile)

Max Activating Token Index: 592

Text #17

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.5148. Min Act: -0.0000

Data Index: 1098372 (The Pile)

Max Activating Token Index: 429

Text #18

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.5009. Min Act: -0.0000

Data Index: 1111802 (The Pile)

Max Activating Token Index: 737

Text #19

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.4976. Min Act: -0.0000

Data Index: 901649 (The Pile)

Max Activating Token Index: 906