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

Dataset: The Pile

Neuron 1947 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: 0.8659. Min Range: -0.8659

Max Act: 0.8659. Min Act: -0.0000

Data Index: 893331 (The Pile)

Max Activating Token Index: 960

Text #1

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.8360. Min Act: -0.0000

Data Index: 377310 (The Pile)

Max Activating Token Index: 1010

Text #2

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.7578. Min Act: -0.0000

Data Index: 1070491 (The Pile)

Max Activating Token Index: 485

Text #3

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.7813. Min Act: -0.0000

Data Index: 1792078 (The Pile)

Max Activating Token Index: 526

Text #4

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.8364. Min Act: -0.0000

Data Index: 966516 (The Pile)

Max Activating Token Index: 770

Text #5

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.7124. Min Act: -0.0000

Data Index: 1378911 (The Pile)

Max Activating Token Index: 123

Text #6

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.5751. Min Act: -0.0000

Data Index: 3494 (The Pile)

Max Activating Token Index: 935

Text #7

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.6053. Min Act: -0.0000

Data Index: 1527208 (The Pile)

Max Activating Token Index: 832

Text #8

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.5901. Min Act: -0.0000

Data Index: 327879 (The Pile)

Max Activating Token Index: 181

Text #9

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.7123. Min Act: -0.0000

Data Index: 858855 (The Pile)

Max Activating Token Index: 444

Text #10

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.6015. Min Act: -0.0000

Data Index: 532474 (The Pile)

Max Activating Token Index: 66

Text #11

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.6766. Min Act: -0.0000

Data Index: 1805134 (The Pile)

Max Activating Token Index: 645

Text #12

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.5985. Min Act: -0.0000

Data Index: 529337 (The Pile)

Max Activating Token Index: 68

Text #13

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.5742. Min Act: -0.0000

Data Index: 1626919 (The Pile)

Max Activating Token Index: 930

Text #14

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.7370. Min Act: -0.0000

Data Index: 1392159 (The Pile)

Max Activating Token Index: 868

Text #15

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.6005. Min Act: -0.0000

Data Index: 1895597 (The Pile)

Max Activating Token Index: 845

Text #16

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.5874. Min Act: -0.0000

Data Index: 1415708 (The Pile)

Max Activating Token Index: 748

Text #17

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.5863. Min Act: -0.0000

Data Index: 281896 (The Pile)

Max Activating Token Index: 314

Text #18

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.7231. Min Act: -0.0000

Data Index: 1910048 (The Pile)

Max Activating Token Index: 612

Text #19

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.5978. Min Act: -0.0000

Data Index: 1667959 (The Pile)

Max Activating Token Index: 668