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

Dataset: The Pile

Neuron 1463 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6112. Min Range: -0.6112

Max Act: 0.6112. Min Act: -0.0000

Data Index: 1122596 (The Pile)

Max Activating Token Index: 530

Text #1

Max Range: 0.6112. Min Range: -0.6112

Max Act: 0.5718. Min Act: -0.0000

Data Index: 380082 (The Pile)

Max Activating Token Index: 308

Text #2

Max Range: 0.6112. Min Range: -0.6112

Max Act: 0.5710. Min Act: -0.0000

Data Index: 1068887 (The Pile)

Max Activating Token Index: 189

Text #3

Max Range: 0.6112. Min Range: -0.6112

Max Act: 0.4996. Min Act: 0.0000

Data Index: 639387 (The Pile)

Max Activating Token Index: 900

Text #4

Max Range: 0.6112. Min Range: -0.6112

Max Act: 0.5124. Min Act: -0.0000

Data Index: 101273 (The Pile)

Max Activating Token Index: 229

Text #5

Max Range: 0.6112. Min Range: -0.6112

Max Act: 0.4930. Min Act: 0.0000

Data Index: 1968100 (The Pile)

Max Activating Token Index: 560

Text #6

Max Range: 0.6112. Min Range: -0.6112

Max Act: 0.4966. Min Act: -0.0000

Data Index: 1863729 (The Pile)

Max Activating Token Index: 402

Text #7

Max Range: 0.6112. Min Range: -0.6112

Max Act: 0.4806. Min Act: 0.0000

Data Index: 1840097 (The Pile)

Max Activating Token Index: 395

Text #8

Max Range: 0.6112. Min Range: -0.6112

Max Act: 0.4878. Min Act: -0.0000

Data Index: 287346 (The Pile)

Max Activating Token Index: 542

Text #9

Max Range: 0.6112. Min Range: -0.6112

Max Act: 0.4801. Min Act: -0.0000

Data Index: 1807162 (The Pile)

Max Activating Token Index: 1010

Text #10

Max Range: 0.6112. Min Range: -0.6112

Max Act: 0.4861. Min Act: -0.0000

Data Index: 1878771 (The Pile)

Max Activating Token Index: 129

Text #11

Max Range: 0.6112. Min Range: -0.6112

Max Act: 0.4771. Min Act: -0.0000

Data Index: 1867795 (The Pile)

Max Activating Token Index: 156

Text #12

Max Range: 0.6112. Min Range: -0.6112

Max Act: 0.4904. Min Act: -0.0000

Data Index: 1053827 (The Pile)

Max Activating Token Index: 312

Text #13

Max Range: 0.6112. Min Range: -0.6112

Max Act: 0.4614. Min Act: -0.0000

Data Index: 1461509 (The Pile)

Max Activating Token Index: 110

Text #14

Max Range: 0.6112. Min Range: -0.6112

Max Act: 0.4782. Min Act: -0.0000

Data Index: 1642687 (The Pile)

Max Activating Token Index: 428

Text #15

Max Range: 0.6112. Min Range: -0.6112

Max Act: 0.4778. Min Act: -0.0000

Data Index: 1905870 (The Pile)

Max Activating Token Index: 927

Text #16

Max Range: 0.6112. Min Range: -0.6112

Max Act: 0.4858. Min Act: -0.0000

Data Index: 1842848 (The Pile)

Max Activating Token Index: 376

Text #17

Max Range: 0.6112. Min Range: -0.6112

Max Act: 0.4509. Min Act: 0.0000

Data Index: 1569833 (The Pile)

Max Activating Token Index: 165

Text #18

Max Range: 0.6112. Min Range: -0.6112

Max Act: 0.4304. Min Act: -0.0000

Data Index: 1431689 (The Pile)

Max Activating Token Index: 315

Text #19

Max Range: 0.6112. Min Range: -0.6112

Max Act: 0.4254. Min Act: -0.0000

Data Index: 1402093 (The Pile)

Max Activating Token Index: 576