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

Dataset: The Pile

Neuron 2970 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3546. Min Range: -1.3546

Max Act: 1.3546. Min Act: -0.0000

Data Index: 769793 (The Pile)

Max Activating Token Index: 252

Text #1

Max Range: 1.3546. Min Range: -1.3546

Max Act: 1.2082. Min Act: -0.0000

Data Index: 272693 (The Pile)

Max Activating Token Index: 570

Text #2

Max Range: 1.3546. Min Range: -1.3546

Max Act: 1.1373. Min Act: -0.0000

Data Index: 171392 (The Pile)

Max Activating Token Index: 406

Text #3

Max Range: 1.3546. Min Range: -1.3546

Max Act: 1.0936. Min Act: -0.0000

Data Index: 496717 (The Pile)

Max Activating Token Index: 1007

Text #4

Max Range: 1.3546. Min Range: -1.3546

Max Act: 1.0414. Min Act: -0.0000

Data Index: 1057091 (The Pile)

Max Activating Token Index: 632

Text #5

Max Range: 1.3546. Min Range: -1.3546

Max Act: 1.0736. Min Act: -0.0000

Data Index: 126936 (The Pile)

Max Activating Token Index: 400

Text #6

Max Range: 1.3546. Min Range: -1.3546

Max Act: 0.9965. Min Act: -0.0000

Data Index: 40372 (The Pile)

Max Activating Token Index: 667

Text #7

Max Range: 1.3546. Min Range: -1.3546

Max Act: 0.9222. Min Act: -0.0000

Data Index: 1631732 (The Pile)

Max Activating Token Index: 212

Text #8

Max Range: 1.3546. Min Range: -1.3546

Max Act: 0.9304. Min Act: -0.0000

Data Index: 1735326 (The Pile)

Max Activating Token Index: 836

Text #9

Max Range: 1.3546. Min Range: -1.3546

Max Act: 0.9957. Min Act: -0.0000

Data Index: 598019 (The Pile)

Max Activating Token Index: 667

Text #10

Max Range: 1.3546. Min Range: -1.3546

Max Act: 0.9106. Min Act: -0.0000

Data Index: 1386194 (The Pile)

Max Activating Token Index: 744

Text #11

Max Range: 1.3546. Min Range: -1.3546

Max Act: 0.9840. Min Act: -0.0000

Data Index: 466884 (The Pile)

Max Activating Token Index: 779

Text #12

Max Range: 1.3546. Min Range: -1.3546

Max Act: 0.8528. Min Act: -0.0000

Data Index: 719551 (The Pile)

Max Activating Token Index: 625

Text #13

Max Range: 1.3546. Min Range: -1.3546

Max Act: 0.9269. Min Act: -0.0000

Data Index: 715044 (The Pile)

Max Activating Token Index: 840

Text #14

Max Range: 1.3546. Min Range: -1.3546

Max Act: 0.9115. Min Act: -0.0000

Data Index: 111803 (The Pile)

Max Activating Token Index: 975

Text #15

Max Range: 1.3546. Min Range: -1.3546

Max Act: 0.8841. Min Act: -0.0000

Data Index: 272955 (The Pile)

Max Activating Token Index: 136

Text #16

Max Range: 1.3546. Min Range: -1.3546

Max Act: 0.7853. Min Act: -0.0000

Data Index: 1991077 (The Pile)

Max Activating Token Index: 962

Text #17

Max Range: 1.3546. Min Range: -1.3546

Max Act: 0.7795. Min Act: -0.0000

Data Index: 830934 (The Pile)

Max Activating Token Index: 636

Text #18

Max Range: 1.3546. Min Range: -1.3546

Max Act: 0.7479. Min Act: -0.0000

Data Index: 27728 (The Pile)

Max Activating Token Index: 59

Text #19

Max Range: 1.3546. Min Range: -1.3546

Max Act: 0.8092. Min Act: -0.0000

Data Index: 1027260 (The Pile)

Max Activating Token Index: 1001