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

Dataset: The Pile

Neuron 855 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: 3.0056. Min Range: -3.0056

Max Act: 3.0056. Min Act: -0.0000

Data Index: 1836249 (The Pile)

Max Activating Token Index: 198

Text #1

Max Range: 3.0056. Min Range: -3.0056

Max Act: 2.7737. Min Act: -0.0000

Data Index: 1683334 (The Pile)

Max Activating Token Index: 178

Text #2

Max Range: 3.0056. Min Range: -3.0056

Max Act: 2.7081. Min Act: -0.0000

Data Index: 1050995 (The Pile)

Max Activating Token Index: 552

Text #3

Max Range: 3.0056. Min Range: -3.0056

Max Act: 2.5376. Min Act: -0.0000

Data Index: 739322 (The Pile)

Max Activating Token Index: 822

Text #4

Max Range: 3.0056. Min Range: -3.0056

Max Act: 2.5005. Min Act: -0.0000

Data Index: 1450758 (The Pile)

Max Activating Token Index: 929

Text #5

Max Range: 3.0056. Min Range: -3.0056

Max Act: 2.3822. Min Act: -0.0000

Data Index: 1370294 (The Pile)

Max Activating Token Index: 907

Text #6

Max Range: 3.0056. Min Range: -3.0056

Max Act: 2.3669. Min Act: -0.0000

Data Index: 1590960 (The Pile)

Max Activating Token Index: 870

Text #7

Max Range: 3.0056. Min Range: -3.0056

Max Act: 2.3630. Min Act: -0.0000

Data Index: 1688636 (The Pile)

Max Activating Token Index: 620

Text #8

Max Range: 3.0056. Min Range: -3.0056

Max Act: 2.4636. Min Act: -0.0000

Data Index: 1428826 (The Pile)

Max Activating Token Index: 199

Text #9

Max Range: 3.0056. Min Range: -3.0056

Max Act: 2.5884. Min Act: -0.0000

Data Index: 267092 (The Pile)

Max Activating Token Index: 864

Text #10

Max Range: 3.0056. Min Range: -3.0056

Max Act: 2.5456. Min Act: -0.0000

Data Index: 272664 (The Pile)

Max Activating Token Index: 779

Text #11

Max Range: 3.0056. Min Range: -3.0056

Max Act: 2.2598. Min Act: -0.0000

Data Index: 942355 (The Pile)

Max Activating Token Index: 842

Text #12

Max Range: 3.0056. Min Range: -3.0056

Max Act: 2.3632. Min Act: -0.0000

Data Index: 140167 (The Pile)

Max Activating Token Index: 55

Text #13

Max Range: 3.0056. Min Range: -3.0056

Max Act: 2.3421. Min Act: -0.0000

Data Index: 176954 (The Pile)

Max Activating Token Index: 23

Text #14

Max Range: 3.0056. Min Range: -3.0056

Max Act: 2.2124. Min Act: -0.0000

Data Index: 649729 (The Pile)

Max Activating Token Index: 23

Text #15

Max Range: 3.0056. Min Range: -3.0056

Max Act: 2.2141. Min Act: -0.0000

Data Index: 518122 (The Pile)

Max Activating Token Index: 778

Text #16

Max Range: 3.0056. Min Range: -3.0056

Max Act: 2.3087. Min Act: -0.0000

Data Index: 1000020 (The Pile)

Max Activating Token Index: 77

Text #17

Max Range: 3.0056. Min Range: -3.0056

Max Act: 2.3923. Min Act: -0.0000

Data Index: 1923143 (The Pile)

Max Activating Token Index: 667

Text #18

Max Range: 3.0056. Min Range: -3.0056

Max Act: 2.1616. Min Act: -0.0000

Data Index: 551461 (The Pile)

Max Activating Token Index: 211

Text #19

Max Range: 3.0056. Min Range: -3.0056

Max Act: 2.1382. Min Act: -0.0000

Data Index: 1595746 (The Pile)

Max Activating Token Index: 110