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

Dataset: The Pile

Neuron 3209 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6878. Min Range: -3.6878

Max Act: 3.5344. Min Act: -0.0000

Data Index: 530535 (The Pile)

Max Activating Token Index: 831

Text #1

Max Range: 3.6878. Min Range: -3.6878

Max Act: 3.6878. Min Act: -0.0000

Data Index: 33278 (The Pile)

Max Activating Token Index: 684

Text #2

Max Range: 3.6878. Min Range: -3.6878

Max Act: 3.5078. Min Act: -0.0000

Data Index: 1038727 (The Pile)

Max Activating Token Index: 12

Text #3

Max Range: 3.6878. Min Range: -3.6878

Max Act: 3.4617. Min Act: -0.0000

Data Index: 737494 (The Pile)

Max Activating Token Index: 11

Text #4

Max Range: 3.6878. Min Range: -3.6878

Max Act: 3.3666. Min Act: -0.0000

Data Index: 1922031 (The Pile)

Max Activating Token Index: 319

Text #5

Max Range: 3.6878. Min Range: -3.6878

Max Act: 3.1210. Min Act: -0.0000

Data Index: 825262 (The Pile)

Max Activating Token Index: 976

Text #6

Max Range: 3.6878. Min Range: -3.6878

Max Act: 3.3943. Min Act: -0.0000

Data Index: 377925 (The Pile)

Max Activating Token Index: 925

Text #7

Max Range: 3.6878. Min Range: -3.6878

Max Act: 3.3595. Min Act: -0.0000

Data Index: 973590 (The Pile)

Max Activating Token Index: 515

Text #8

Max Range: 3.6878. Min Range: -3.6878

Max Act: 2.9621. Min Act: -0.0000

Data Index: 214391 (The Pile)

Max Activating Token Index: 771

Text #9

Max Range: 3.6878. Min Range: -3.6878

Max Act: 3.1520. Min Act: -0.0000

Data Index: 871365 (The Pile)

Max Activating Token Index: 547

Text #10

Max Range: 3.6878. Min Range: -3.6878

Max Act: 2.8105. Min Act: -0.0000

Data Index: 1702243 (The Pile)

Max Activating Token Index: 731

Text #11

Max Range: 3.6878. Min Range: -3.6878

Max Act: 3.0795. Min Act: -0.0000

Data Index: 26949 (The Pile)

Max Activating Token Index: 380

Text #12

Max Range: 3.6878. Min Range: -3.6878

Max Act: 3.1883. Min Act: -0.0000

Data Index: 468220 (The Pile)

Max Activating Token Index: 707

Text #13

Max Range: 3.6878. Min Range: -3.6878

Max Act: 3.1991. Min Act: -0.0000

Data Index: 244793 (The Pile)

Max Activating Token Index: 524

Text #14

Max Range: 3.6878. Min Range: -3.6878

Max Act: 3.2032. Min Act: -0.0000

Data Index: 1278074 (The Pile)

Max Activating Token Index: 509

Text #15

Max Range: 3.6878. Min Range: -3.6878

Max Act: 3.4867. Min Act: -0.0000

Data Index: 1705086 (The Pile)

Max Activating Token Index: 583

Text #16

Max Range: 3.6878. Min Range: -3.6878

Max Act: 3.1750. Min Act: -0.0000

Data Index: 1602979 (The Pile)

Max Activating Token Index: 547

Text #17

Max Range: 3.6878. Min Range: -3.6878

Max Act: 3.0069. Min Act: -0.0000

Data Index: 1674691 (The Pile)

Max Activating Token Index: 444

Text #18

Max Range: 3.6878. Min Range: -3.6878

Max Act: 3.1678. Min Act: -0.0000

Data Index: 1640439 (The Pile)

Max Activating Token Index: 600

Text #19

Max Range: 3.6878. Min Range: -3.6878

Max Act: 3.4009. Min Act: -0.0000

Data Index: 1993595 (The Pile)

Max Activating Token Index: 720