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

Dataset: The Pile

Neuron 3919 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: 0.8750. Min Range: -0.8750

Max Act: 0.8750. Min Act: -0.0000

Data Index: 1754463 (The Pile)

Max Activating Token Index: 70

Text #1

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.8173. Min Act: -0.0000

Data Index: 1208128 (The Pile)

Max Activating Token Index: 698

Text #2

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.7689. Min Act: -0.0000

Data Index: 117967 (The Pile)

Max Activating Token Index: 623

Text #3

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.7853. Min Act: -0.0000

Data Index: 320758 (The Pile)

Max Activating Token Index: 364

Text #4

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.7104. Min Act: -0.0000

Data Index: 1756172 (The Pile)

Max Activating Token Index: 335

Text #5

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.6538. Min Act: -0.0000

Data Index: 348255 (The Pile)

Max Activating Token Index: 844

Text #6

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.7553. Min Act: -0.0000

Data Index: 865667 (The Pile)

Max Activating Token Index: 72

Text #7

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.6945. Min Act: -0.0000

Data Index: 397661 (The Pile)

Max Activating Token Index: 651

Text #8

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.7475. Min Act: -0.0000

Data Index: 1837752 (The Pile)

Max Activating Token Index: 860

Text #9

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.7302. Min Act: -0.0000

Data Index: 90152 (The Pile)

Max Activating Token Index: 168

Text #10

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.6362. Min Act: -0.0000

Data Index: 1015718 (The Pile)

Max Activating Token Index: 967

Text #11

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.7228. Min Act: -0.0000

Data Index: 1510682 (The Pile)

Max Activating Token Index: 765

Text #12

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.6801. Min Act: -0.0000

Data Index: 1051401 (The Pile)

Max Activating Token Index: 60

Text #13

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.6509. Min Act: -0.0000

Data Index: 1632393 (The Pile)

Max Activating Token Index: 185

Text #14

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.6524. Min Act: -0.0000

Data Index: 482165 (The Pile)

Max Activating Token Index: 165

Text #15

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.6520. Min Act: -0.0000

Data Index: 1495982 (The Pile)

Max Activating Token Index: 325

Text #16

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.6145. Min Act: -0.0000

Data Index: 857085 (The Pile)

Max Activating Token Index: 58

Text #17

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.6423. Min Act: -0.0000

Data Index: 1558910 (The Pile)

Max Activating Token Index: 298

Text #18

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.6239. Min Act: -0.0000

Data Index: 5685 (The Pile)

Max Activating Token Index: 948

Text #19

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.6580. Min Act: -0.0000

Data Index: 397308 (The Pile)

Max Activating Token Index: 387