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

Dataset: The Pile

Neuron 638 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: 1.0128. Min Range: -1.0128

Max Act: 1.0128. Min Act: 0.0000

Data Index: 125167 (The Pile)

Max Activating Token Index: 757

Text #1

Max Range: 1.0128. Min Range: -1.0128

Max Act: 0.8813. Min Act: -0.0000

Data Index: 1067898 (The Pile)

Max Activating Token Index: 574

Text #2

Max Range: 1.0128. Min Range: -1.0128

Max Act: 0.8420. Min Act: -0.0000

Data Index: 1051063 (The Pile)

Max Activating Token Index: 346

Text #3

Max Range: 1.0128. Min Range: -1.0128

Max Act: 0.8353. Min Act: -0.0000

Data Index: 1209366 (The Pile)

Max Activating Token Index: 39

Text #4

Max Range: 1.0128. Min Range: -1.0128

Max Act: 0.8378. Min Act: 0.0000

Data Index: 1553374 (The Pile)

Max Activating Token Index: 69

Text #5

Max Range: 1.0128. Min Range: -1.0128

Max Act: 0.7472. Min Act: -0.0000

Data Index: 143660 (The Pile)

Max Activating Token Index: 387

Text #6

Max Range: 1.0128. Min Range: -1.0128

Max Act: 0.7566. Min Act: 0.0000

Data Index: 1229590 (The Pile)

Max Activating Token Index: 322

Text #7

Max Range: 1.0128. Min Range: -1.0128

Max Act: 0.7330. Min Act: -0.0000

Data Index: 655925 (The Pile)

Max Activating Token Index: 1013

Text #8

Max Range: 1.0128. Min Range: -1.0128

Max Act: 0.7098. Min Act: -0.0000

Data Index: 1735812 (The Pile)

Max Activating Token Index: 971

Text #9

Max Range: 1.0128. Min Range: -1.0128

Max Act: 0.7640. Min Act: -0.0000

Data Index: 51362 (The Pile)

Max Activating Token Index: 176

Text #10

Max Range: 1.0128. Min Range: -1.0128

Max Act: 0.6649. Min Act: -0.0000

Data Index: 512881 (The Pile)

Max Activating Token Index: 892

Text #11

Max Range: 1.0128. Min Range: -1.0128

Max Act: 0.6950. Min Act: -0.0000

Data Index: 842344 (The Pile)

Max Activating Token Index: 779

Text #12

Max Range: 1.0128. Min Range: -1.0128

Max Act: 0.6456. Min Act: -0.0000

Data Index: 1200301 (The Pile)

Max Activating Token Index: 344

Text #13

Max Range: 1.0128. Min Range: -1.0128

Max Act: 0.6925. Min Act: -0.0000

Data Index: 1058728 (The Pile)

Max Activating Token Index: 893

Text #14

Max Range: 1.0128. Min Range: -1.0128

Max Act: 0.6514. Min Act: -0.0000

Data Index: 729651 (The Pile)

Max Activating Token Index: 706

Text #15

Max Range: 1.0128. Min Range: -1.0128

Max Act: 0.6917. Min Act: -0.0000

Data Index: 801657 (The Pile)

Max Activating Token Index: 924

Text #16

Max Range: 1.0128. Min Range: -1.0128

Max Act: 0.6697. Min Act: -0.0000

Data Index: 891867 (The Pile)

Max Activating Token Index: 870

Text #17

Max Range: 1.0128. Min Range: -1.0128

Max Act: 0.6793. Min Act: -0.0000

Data Index: 1479430 (The Pile)

Max Activating Token Index: 869

Text #18

Max Range: 1.0128. Min Range: -1.0128

Max Act: 0.6035. Min Act: -0.0000

Data Index: 310243 (The Pile)

Max Activating Token Index: 195

Text #19

Max Range: 1.0128. Min Range: -1.0128

Max Act: 0.6238. Min Act: -0.0000

Data Index: 1153464 (The Pile)

Max Activating Token Index: 767