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

Dataset: The Pile

Neuron 4175 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: 0.2679. Min Range: -0.2679

Max Act: 0.2679. Min Act: -0.0000

Data Index: 1084405 (The Pile)

Max Activating Token Index: 64

Text #1

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.2466. Min Act: -0.0000

Data Index: 771828 (The Pile)

Max Activating Token Index: 147

Text #2

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.2259. Min Act: -0.0000

Data Index: 702499 (The Pile)

Max Activating Token Index: 599

Text #3

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.2001. Min Act: -0.0000

Data Index: 1072438 (The Pile)

Max Activating Token Index: 448

Text #4

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1792. Min Act: -0.0000

Data Index: 1391445 (The Pile)

Max Activating Token Index: 985

Text #5

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1957. Min Act: -0.0000

Data Index: 319077 (The Pile)

Max Activating Token Index: 657

Text #6

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1892. Min Act: -0.0000

Data Index: 1087325 (The Pile)

Max Activating Token Index: 605

Text #7

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1757. Min Act: -0.0000

Data Index: 855346 (The Pile)

Max Activating Token Index: 706

Text #8

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1862. Min Act: -0.0000

Data Index: 1106895 (The Pile)

Max Activating Token Index: 42

Text #9

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1925. Min Act: -0.0000

Data Index: 1871069 (The Pile)

Max Activating Token Index: 997

Text #10

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1744. Min Act: -0.0000

Data Index: 1936612 (The Pile)

Max Activating Token Index: 962

Text #11

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1752. Min Act: -0.0000

Data Index: 644065 (The Pile)

Max Activating Token Index: 140

Text #12

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1552. Min Act: -0.0000

Data Index: 76549 (The Pile)

Max Activating Token Index: 964

Text #13

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1620. Min Act: -0.0000

Data Index: 654439 (The Pile)

Max Activating Token Index: 740

Text #14

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1777. Min Act: -0.0000

Data Index: 1969601 (The Pile)

Max Activating Token Index: 905

Text #15

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1655. Min Act: -0.0000

Data Index: 1482622 (The Pile)

Max Activating Token Index: 915

Text #16

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1903. Min Act: -0.0000

Data Index: 1364142 (The Pile)

Max Activating Token Index: 84

Text #17

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1661. Min Act: -0.0000

Data Index: 737243 (The Pile)

Max Activating Token Index: 663

Text #18

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1726. Min Act: -0.0000

Data Index: 409207 (The Pile)

Max Activating Token Index: 233

Text #19

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1929. Min Act: -0.0000

Data Index: 1620472 (The Pile)

Max Activating Token Index: 438