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

Dataset: The Pile

Neuron 3482 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: 3.9707. Min Range: -3.9707

Max Act: 3.9707. Min Act: -0.0000

Data Index: 942172 (The Pile)

Max Activating Token Index: 350

Text #1

Max Range: 3.9707. Min Range: -3.9707

Max Act: 3.8138. Min Act: -0.0000

Data Index: 1598069 (The Pile)

Max Activating Token Index: 513

Text #2

Max Range: 3.9707. Min Range: -3.9707

Max Act: 3.6573. Min Act: -0.0000

Data Index: 123709 (The Pile)

Max Activating Token Index: 629

Text #3

Max Range: 3.9707. Min Range: -3.9707

Max Act: 3.5514. Min Act: -0.0000

Data Index: 654025 (The Pile)

Max Activating Token Index: 817

Text #4

Max Range: 3.9707. Min Range: -3.9707

Max Act: 3.5038. Min Act: -0.0000

Data Index: 713785 (The Pile)

Max Activating Token Index: 778

Text #5

Max Range: 3.9707. Min Range: -3.9707

Max Act: 3.6707. Min Act: -0.0000

Data Index: 353505 (The Pile)

Max Activating Token Index: 782

Text #6

Max Range: 3.9707. Min Range: -3.9707

Max Act: 3.0984. Min Act: -0.0000

Data Index: 1947842 (The Pile)

Max Activating Token Index: 73

Text #7

Max Range: 3.9707. Min Range: -3.9707

Max Act: 3.1903. Min Act: -0.0000

Data Index: 505684 (The Pile)

Max Activating Token Index: 565

Text #8

Max Range: 3.9707. Min Range: -3.9707

Max Act: 2.9305. Min Act: -0.0000

Data Index: 1846715 (The Pile)

Max Activating Token Index: 92

Text #9

Max Range: 3.9707. Min Range: -3.9707

Max Act: 2.8358. Min Act: -0.0000

Data Index: 1755909 (The Pile)

Max Activating Token Index: 620

Text #10

Max Range: 3.9707. Min Range: -3.9707

Max Act: 2.9472. Min Act: -0.0000

Data Index: 990424 (The Pile)

Max Activating Token Index: 65

Text #11

Max Range: 3.9707. Min Range: -3.9707

Max Act: 2.8934. Min Act: -0.0000

Data Index: 1877674 (The Pile)

Max Activating Token Index: 72

Text #12

Max Range: 3.9707. Min Range: -3.9707

Max Act: 2.8873. Min Act: -0.0000

Data Index: 388941 (The Pile)

Max Activating Token Index: 177

Text #13

Max Range: 3.9707. Min Range: -3.9707

Max Act: 2.8496. Min Act: -0.0000

Data Index: 341427 (The Pile)

Max Activating Token Index: 110

Text #14

Max Range: 3.9707. Min Range: -3.9707

Max Act: 2.8118. Min Act: -0.0000

Data Index: 900024 (The Pile)

Max Activating Token Index: 53

Text #15

Max Range: 3.9707. Min Range: -3.9707

Max Act: 2.8000. Min Act: -0.0000

Data Index: 1688242 (The Pile)

Max Activating Token Index: 165

Text #16

Max Range: 3.9707. Min Range: -3.9707

Max Act: 2.6658. Min Act: -0.0000

Data Index: 768312 (The Pile)

Max Activating Token Index: 557

Text #17

Max Range: 3.9707. Min Range: -3.9707

Max Act: 2.7694. Min Act: -0.0000

Data Index: 1913410 (The Pile)

Max Activating Token Index: 996

Text #18

Max Range: 3.9707. Min Range: -3.9707

Max Act: 2.4668. Min Act: -0.0000

Data Index: 622878 (The Pile)

Max Activating Token Index: 617

Text #19

Max Range: 3.9707. Min Range: -3.9707

Max Act: 2.5922. Min Act: -0.0000

Data Index: 1766792 (The Pile)

Max Activating Token Index: 488