Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4792 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9923. Min Range: -2.9923

Max Act: 2.9923. Min Act: -0.0000

Data Index: 47555 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 2.9923. Min Range: -2.9923

Max Act: 2.5283. Min Act: 0.0000

Data Index: 837597 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 2.9923. Min Range: -2.9923

Max Act: 2.1217. Min Act: 0.0000

Data Index: 1061400 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 2.9923. Min Range: -2.9923

Max Act: 2.0485. Min Act: -0.0000

Data Index: 1157390 (C4 (Web Text))

Max Activating Token Index: 825

Text #4

Max Range: 2.9923. Min Range: -2.9923

Max Act: 2.0543. Min Act: -0.0000

Data Index: 1180934 (C4 (Web Text))

Max Activating Token Index: 741

Text #5

Max Range: 2.9923. Min Range: -2.9923

Max Act: 1.9354. Min Act: -0.0000

Data Index: 1342015 (C4 (Web Text))

Max Activating Token Index: 549

Text #6

Max Range: 2.9923. Min Range: -2.9923

Max Act: 2.0857. Min Act: -0.0000

Data Index: 23205 (C4 (Web Text))

Max Activating Token Index: 1012

Text #7

Max Range: 2.9923. Min Range: -2.9923

Max Act: 1.9914. Min Act: -0.0000

Data Index: 715219 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 2.9923. Min Range: -2.9923

Max Act: 1.8711. Min Act: -0.0000

Data Index: 27903 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 2.9923. Min Range: -2.9923

Max Act: 2.1513. Min Act: -0.0000

Data Index: 882914 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 2.9923. Min Range: -2.9923

Max Act: 1.9179. Min Act: -0.0000

Data Index: 627070 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 2.9923. Min Range: -2.9923

Max Act: 1.8897. Min Act: -0.0000

Data Index: 1010528 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 2.9923. Min Range: -2.9923

Max Act: 1.8763. Min Act: -0.0000

Data Index: 65604 (C4 (Web Text))

Max Activating Token Index: 573

Text #13

Max Range: 2.9923. Min Range: -2.9923

Max Act: 2.0507. Min Act: -0.0000

Data Index: 1182918 (C4 (Web Text))

Max Activating Token Index: 696

Text #14

Max Range: 2.9923. Min Range: -2.9923

Max Act: 1.7258. Min Act: -0.0000

Data Index: 1346044 (C4 (Web Text))

Max Activating Token Index: 929

Text #15

Max Range: 2.9923. Min Range: -2.9923

Max Act: 1.9010. Min Act: -0.0000

Data Index: 47337 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 2.9923. Min Range: -2.9923

Max Act: 1.7961. Min Act: 0.0000

Data Index: 1202534 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 2.9923. Min Range: -2.9923

Max Act: 1.7756. Min Act: -0.0000

Data Index: 794916 (C4 (Web Text))

Max Activating Token Index: 481

Text #18

Max Range: 2.9923. Min Range: -2.9923

Max Act: 1.7535. Min Act: -0.0000

Data Index: 873001 (C4 (Web Text))

Max Activating Token Index: 530

Text #19

Max Range: 2.9923. Min Range: -2.9923

Max Act: 1.6187. Min Act: -0.0000

Data Index: 1297673 (C4 (Web Text))

Max Activating Token Index: 540