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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2162 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0764. Min Range: -2.0764

Max Act: 2.0764. Min Act: -0.0000

Data Index: 655919 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 2.0764. Min Range: -2.0764

Max Act: 1.8937. Min Act: -0.0000

Data Index: 510716 (C4 (Web Text))

Max Activating Token Index: 415

Text #2

Max Range: 2.0764. Min Range: -2.0764

Max Act: 1.5792. Min Act: -0.0000

Data Index: 625884 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 2.0764. Min Range: -2.0764

Max Act: 1.4771. Min Act: -0.0000

Data Index: 184529 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 2.0764. Min Range: -2.0764

Max Act: 1.4285. Min Act: -0.0000

Data Index: 393352 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 2.0764. Min Range: -2.0764

Max Act: 1.3797. Min Act: -0.0000

Data Index: 1248102 (C4 (Web Text))

Max Activating Token Index: 486

Text #6

Max Range: 2.0764. Min Range: -2.0764

Max Act: 1.3298. Min Act: -0.0000

Data Index: 314458 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 2.0764. Min Range: -2.0764

Max Act: 1.4005. Min Act: -0.0000

Data Index: 100386 (C4 (Web Text))

Max Activating Token Index: 92

Text #8

Max Range: 2.0764. Min Range: -2.0764

Max Act: 1.3978. Min Act: -0.0000

Data Index: 1351842 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 2.0764. Min Range: -2.0764

Max Act: 1.3587. Min Act: -0.0000

Data Index: 500254 (C4 (Web Text))

Max Activating Token Index: 696

Text #10

Max Range: 2.0764. Min Range: -2.0764

Max Act: 1.4879. Min Act: -0.0000

Data Index: 82539 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 2.0764. Min Range: -2.0764

Max Act: 1.3525. Min Act: -0.0000

Data Index: 1033007 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 2.0764. Min Range: -2.0764

Max Act: 1.3836. Min Act: -0.0000

Data Index: 1184771 (C4 (Web Text))

Max Activating Token Index: 916

Text #13

Max Range: 2.0764. Min Range: -2.0764

Max Act: 1.3798. Min Act: -0.0000

Data Index: 393974 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 2.0764. Min Range: -2.0764

Max Act: 1.3274. Min Act: -0.0000

Data Index: 225812 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 2.0764. Min Range: -2.0764

Max Act: 1.3691. Min Act: -0.0000

Data Index: 924424 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 2.0764. Min Range: -2.0764

Max Act: 1.4399. Min Act: -0.0000

Data Index: 304130 (C4 (Web Text))

Max Activating Token Index: 660

Text #17

Max Range: 2.0764. Min Range: -2.0764

Max Act: 1.2564. Min Act: -0.0000

Data Index: 1072841 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 2.0764. Min Range: -2.0764

Max Act: 1.3387. Min Act: -0.0000

Data Index: 952332 (C4 (Web Text))

Max Activating Token Index: 731

Text #19

Max Range: 2.0764. Min Range: -2.0764

Max Act: 1.2500. Min Act: -0.0000

Data Index: 679113 (C4 (Web Text))

Max Activating Token Index: 841