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

Dataset: The Pile

Neuron 3450 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1668. Min Act: -0.0000

Data Index: 462128 (The Pile)

Max Activating Token Index: 31

Text #1

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1778. Min Act: -0.0000

Data Index: 1024369 (The Pile)

Max Activating Token Index: 103

Text #2

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1590. Min Act: -0.0000

Data Index: 97382 (The Pile)

Max Activating Token Index: 478

Text #3

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1377. Min Act: -0.0000

Data Index: 578854 (The Pile)

Max Activating Token Index: 778

Text #4

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.0818. Min Act: -0.0000

Data Index: 606519 (The Pile)

Max Activating Token Index: 928

Text #5

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1120. Min Act: -0.0000

Data Index: 1141954 (The Pile)

Max Activating Token Index: 574

Text #6

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.0950. Min Act: -0.0000

Data Index: 1816032 (The Pile)

Max Activating Token Index: 419

Text #7

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1242. Min Act: -0.0000

Data Index: 560221 (The Pile)

Max Activating Token Index: 836

Text #8

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.0938. Min Act: -0.0000

Data Index: 1497289 (The Pile)

Max Activating Token Index: 135

Text #9

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1026. Min Act: -0.0000

Data Index: 1178221 (The Pile)

Max Activating Token Index: 95

Text #10

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1068. Min Act: -0.0000

Data Index: 861207 (The Pile)

Max Activating Token Index: 757

Text #11

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1156. Min Act: -0.0000

Data Index: 407651 (The Pile)

Max Activating Token Index: 870

Text #12

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.0966. Min Act: -0.0000

Data Index: 1818792 (The Pile)

Max Activating Token Index: 742

Text #13

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1208. Min Act: -0.0000

Data Index: 30222 (The Pile)

Max Activating Token Index: 732

Text #14

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1064. Min Act: -0.0000

Data Index: 1734442 (The Pile)

Max Activating Token Index: 107

Text #15

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.0982. Min Act: -0.0000

Data Index: 1937692 (The Pile)

Max Activating Token Index: 268

Text #16

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1002. Min Act: -0.0000

Data Index: 1163736 (The Pile)

Max Activating Token Index: 367

Text #17

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1083. Min Act: -0.0000

Data Index: 578687 (The Pile)

Max Activating Token Index: 88

Text #18

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1004. Min Act: -0.0000

Data Index: 335579 (The Pile)

Max Activating Token Index: 289

Text #19

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.0821. Min Act: -0.0000

Data Index: 562303 (The Pile)

Max Activating Token Index: 911