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

Dataset: The Pile

Neuron 695 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.2211. Min Act: -0.0000

Data Index: 883248 (The Pile)

Max Activating Token Index: 622

Text #1

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.2037. Min Act: -0.0000

Data Index: 1003596 (The Pile)

Max Activating Token Index: 53

Text #2

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.2086. Min Act: -0.0000

Data Index: 1376527 (The Pile)

Max Activating Token Index: 400

Text #3

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.2083. Min Act: -0.0000

Data Index: 477493 (The Pile)

Max Activating Token Index: 232

Text #4

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.2004. Min Act: -0.0000

Data Index: 897736 (The Pile)

Max Activating Token Index: 558

Text #5

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.2129. Min Act: -0.0000

Data Index: 1145494 (The Pile)

Max Activating Token Index: 559

Text #6

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.2124. Min Act: -0.0000

Data Index: 1477702 (The Pile)

Max Activating Token Index: 82

Text #7

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.2016. Min Act: -0.0000

Data Index: 149610 (The Pile)

Max Activating Token Index: 670

Text #8

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1946. Min Act: -0.0000

Data Index: 695052 (The Pile)

Max Activating Token Index: 159

Text #9

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.2037. Min Act: -0.0000

Data Index: 1994450 (The Pile)

Max Activating Token Index: 430

Text #10

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1898. Min Act: -0.0000

Data Index: 1203697 (The Pile)

Max Activating Token Index: 373

Text #11

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1885. Min Act: -0.0000

Data Index: 625872 (The Pile)

Max Activating Token Index: 72

Text #12

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1889. Min Act: -0.0000

Data Index: 687370 (The Pile)

Max Activating Token Index: 451

Text #13

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1937. Min Act: -0.0000

Data Index: 244848 (The Pile)

Max Activating Token Index: 717

Text #14

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1847. Min Act: -0.0000

Data Index: 1890692 (The Pile)

Max Activating Token Index: 669

Text #15

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1810. Min Act: -0.0000

Data Index: 357281 (The Pile)

Max Activating Token Index: 28

Text #16

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1662. Min Act: -0.0000

Data Index: 521284 (The Pile)

Max Activating Token Index: 526

Text #17

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1838. Min Act: -0.0000

Data Index: 1356623 (The Pile)

Max Activating Token Index: 95

Text #18

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1763. Min Act: -0.0000

Data Index: 669723 (The Pile)

Max Activating Token Index: 473

Text #19

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1769. Min Act: -0.0000

Data Index: 1911499 (The Pile)

Max Activating Token Index: 778