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

Dataset: The Pile

Neuron 1230 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: 1.9047. Min Range: -1.9047

Max Act: 1.9047. Min Act: -0.0000

Data Index: 1214634 (The Pile)

Max Activating Token Index: 798

Text #1

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.6994. Min Act: -0.0000

Data Index: 1876014 (The Pile)

Max Activating Token Index: 199

Text #2

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.7970. Min Act: -0.0000

Data Index: 367049 (The Pile)

Max Activating Token Index: 488

Text #3

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.7611. Min Act: -0.0000

Data Index: 991109 (The Pile)

Max Activating Token Index: 135

Text #4

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.6719. Min Act: -0.0000

Data Index: 215017 (The Pile)

Max Activating Token Index: 29

Text #5

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.7585. Min Act: -0.0000

Data Index: 1304237 (The Pile)

Max Activating Token Index: 20

Text #6

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.4747. Min Act: -0.0000

Data Index: 1729743 (The Pile)

Max Activating Token Index: 960

Text #7

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.7810. Min Act: -0.0000

Data Index: 948233 (The Pile)

Max Activating Token Index: 750

Text #8

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.6399. Min Act: -0.0000

Data Index: 484124 (The Pile)

Max Activating Token Index: 198

Text #9

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.5164. Min Act: -0.0000

Data Index: 207865 (The Pile)

Max Activating Token Index: 816

Text #10

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.6225. Min Act: -0.0000

Data Index: 1831838 (The Pile)

Max Activating Token Index: 546

Text #11

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.6713. Min Act: -0.0000

Data Index: 893197 (The Pile)

Max Activating Token Index: 848

Text #12

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.6206. Min Act: -0.0000

Data Index: 303129 (The Pile)

Max Activating Token Index: 17

Text #13

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.3972. Min Act: -0.0000

Data Index: 1731078 (The Pile)

Max Activating Token Index: 1018

Text #14

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.6608. Min Act: -0.0000

Data Index: 679999 (The Pile)

Max Activating Token Index: 820

Text #15

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.7285. Min Act: -0.0000

Data Index: 1424427 (The Pile)

Max Activating Token Index: 526

Text #16

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.6348. Min Act: -0.0000

Data Index: 1352634 (The Pile)

Max Activating Token Index: 621

Text #17

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.5681. Min Act: -0.0000

Data Index: 1172440 (The Pile)

Max Activating Token Index: 695

Text #18

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.5721. Min Act: -0.0000

Data Index: 950787 (The Pile)

Max Activating Token Index: 354

Text #19

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.5773. Min Act: -0.0000

Data Index: 1262972 (The Pile)

Max Activating Token Index: 584