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

Dataset: The Pile

Neuron 4754 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: 0.2418. Min Range: -0.2418

Max Act: 0.2418. Min Act: -0.0000

Data Index: 492566 (The Pile)

Max Activating Token Index: 124

Text #1

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.1528. Min Act: -0.0000

Data Index: 1148916 (The Pile)

Max Activating Token Index: 395

Text #2

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.1564. Min Act: -0.0000

Data Index: 564594 (The Pile)

Max Activating Token Index: 963

Text #3

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.1404. Min Act: -0.0000

Data Index: 1878288 (The Pile)

Max Activating Token Index: 834

Text #4

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.1362. Min Act: -0.0000

Data Index: 785511 (The Pile)

Max Activating Token Index: 249

Text #5

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.1251. Min Act: -0.0000

Data Index: 1730619 (The Pile)

Max Activating Token Index: 316

Text #6

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.1186. Min Act: -0.0000

Data Index: 1986749 (The Pile)

Max Activating Token Index: 141

Text #7

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.1155. Min Act: -0.0000

Data Index: 119515 (The Pile)

Max Activating Token Index: 17

Text #8

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.1066. Min Act: -0.0000

Data Index: 641713 (The Pile)

Max Activating Token Index: 351

Text #9

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.1101. Min Act: -0.0000

Data Index: 1800675 (The Pile)

Max Activating Token Index: 548

Text #10

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.0912. Min Act: -0.0000

Data Index: 807623 (The Pile)

Max Activating Token Index: 36

Text #11

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.0995. Min Act: -0.0000

Data Index: 1726010 (The Pile)

Max Activating Token Index: 700

Text #12

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.0855. Min Act: -0.0000

Data Index: 910396 (The Pile)

Max Activating Token Index: 967

Text #13

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.0923. Min Act: -0.0000

Data Index: 790257 (The Pile)

Max Activating Token Index: 72

Text #14

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.1126. Min Act: -0.0000

Data Index: 1904922 (The Pile)

Max Activating Token Index: 784

Text #15

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.0965. Min Act: -0.0000

Data Index: 1745884 (The Pile)

Max Activating Token Index: 807

Text #16

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.0870. Min Act: -0.0000

Data Index: 228763 (The Pile)

Max Activating Token Index: 951

Text #17

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.0892. Min Act: -0.0000

Data Index: 709280 (The Pile)

Max Activating Token Index: 536

Text #18

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.1000. Min Act: -0.0000

Data Index: 1134400 (The Pile)

Max Activating Token Index: 993

Text #19

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.0955. Min Act: -0.0000

Data Index: 498545 (The Pile)

Max Activating Token Index: 298