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

Dataset: The Pile

Neuron 2833 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: 1.8903. Min Range: -1.8903

Max Act: 1.8903. Min Act: -0.0000

Data Index: 1058460 (The Pile)

Max Activating Token Index: 442

Text #1

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.5438. Min Act: -0.0000

Data Index: 1370729 (The Pile)

Max Activating Token Index: 972

Text #2

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.5181. Min Act: -0.0000

Data Index: 1687798 (The Pile)

Max Activating Token Index: 654

Text #3

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.5829. Min Act: -0.0000

Data Index: 1720049 (The Pile)

Max Activating Token Index: 814

Text #4

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.4878. Min Act: -0.0000

Data Index: 171952 (The Pile)

Max Activating Token Index: 524

Text #5

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.4751. Min Act: 0.0000

Data Index: 1912466 (The Pile)

Max Activating Token Index: 593

Text #6

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.4381. Min Act: -0.0000

Data Index: 5598 (The Pile)

Max Activating Token Index: 317

Text #7

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.5070. Min Act: 0.0000

Data Index: 1235695 (The Pile)

Max Activating Token Index: 522

Text #8

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.5076. Min Act: -0.0000

Data Index: 991727 (The Pile)

Max Activating Token Index: 877

Text #9

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.6262. Min Act: -0.0000

Data Index: 1558792 (The Pile)

Max Activating Token Index: 941

Text #10

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.3873. Min Act: -0.0000

Data Index: 975285 (The Pile)

Max Activating Token Index: 996

Text #11

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.3600. Min Act: -0.0000

Data Index: 1484719 (The Pile)

Max Activating Token Index: 670

Text #12

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.3353. Min Act: -0.0000

Data Index: 1620751 (The Pile)

Max Activating Token Index: 987

Text #13

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.3129. Min Act: -0.0000

Data Index: 201917 (The Pile)

Max Activating Token Index: 490

Text #14

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.2481. Min Act: -0.0000

Data Index: 1176773 (The Pile)

Max Activating Token Index: 75

Text #15

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.2944. Min Act: -0.0000

Data Index: 1935458 (The Pile)

Max Activating Token Index: 382

Text #16

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.3710. Min Act: -0.0000

Data Index: 1589771 (The Pile)

Max Activating Token Index: 100

Text #17

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.2802. Min Act: -0.0000

Data Index: 1991240 (The Pile)

Max Activating Token Index: 530

Text #18

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.2389. Min Act: -0.0000

Data Index: 1464385 (The Pile)

Max Activating Token Index: 632

Text #19

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.2986. Min Act: -0.0000

Data Index: 1658620 (The Pile)

Max Activating Token Index: 354