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

Dataset: The Pile

Neuron 9 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.6914. Min Act: -0.0000

Data Index: 107360 (The Pile)

Max Activating Token Index: 16

Text #1

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.6441. Min Act: -0.0000

Data Index: 1412347 (The Pile)

Max Activating Token Index: 481

Text #2

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.6243. Min Act: -0.0000

Data Index: 963288 (The Pile)

Max Activating Token Index: 417

Text #3

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.5965. Min Act: -0.0000

Data Index: 173192 (The Pile)

Max Activating Token Index: 572

Text #4

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.5715. Min Act: -0.0000

Data Index: 1459476 (The Pile)

Max Activating Token Index: 627

Text #5

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.6125. Min Act: -0.0000

Data Index: 873205 (The Pile)

Max Activating Token Index: 915

Text #6

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.5435. Min Act: -0.0000

Data Index: 263814 (The Pile)

Max Activating Token Index: 338

Text #7

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.5934. Min Act: -0.0000

Data Index: 959426 (The Pile)

Max Activating Token Index: 90

Text #8

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.5284. Min Act: -0.0000

Data Index: 1633756 (The Pile)

Max Activating Token Index: 878

Text #9

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.5423. Min Act: -0.0000

Data Index: 651871 (The Pile)

Max Activating Token Index: 158

Text #10

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.5235. Min Act: -0.0000

Data Index: 265330 (The Pile)

Max Activating Token Index: 20

Text #11

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.5195. Min Act: -0.0000

Data Index: 1054650 (The Pile)

Max Activating Token Index: 392

Text #12

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.5020. Min Act: -0.0000

Data Index: 144807 (The Pile)

Max Activating Token Index: 43

Text #13

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.5175. Min Act: -0.0000

Data Index: 657246 (The Pile)

Max Activating Token Index: 526

Text #14

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.5536. Min Act: -0.0000

Data Index: 1055378 (The Pile)

Max Activating Token Index: 14

Text #15

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.5056. Min Act: -0.0000

Data Index: 1932005 (The Pile)

Max Activating Token Index: 772

Text #16

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.4632. Min Act: -0.0000

Data Index: 1135191 (The Pile)

Max Activating Token Index: 240

Text #17

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.4979. Min Act: -0.0000

Data Index: 1209568 (The Pile)

Max Activating Token Index: 481

Text #18

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.5334. Min Act: -0.0000

Data Index: 1022598 (The Pile)

Max Activating Token Index: 869

Text #19

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.4919. Min Act: -0.0000

Data Index: 932247 (The Pile)

Max Activating Token Index: 84