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

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

Neuron 3079 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0111. Min Range: -3.0111

Max Act: 2.8908. Min Act: -0.0000

Data Index: 213948 (C4 (Web Text))

Max Activating Token Index: 188

Text #1

Max Range: 3.0111. Min Range: -3.0111

Max Act: 3.0111. Min Act: -0.0001

Data Index: 689717 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 3.0111. Min Range: -3.0111

Max Act: 2.9039. Min Act: -0.0000

Data Index: 878279 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 3.0111. Min Range: -3.0111

Max Act: 2.8676. Min Act: -0.0001

Data Index: 121080 (C4 (Web Text))

Max Activating Token Index: 630

Text #4

Max Range: 3.0111. Min Range: -3.0111

Max Act: 2.6695. Min Act: -0.0000

Data Index: 915467 (C4 (Web Text))

Max Activating Token Index: 505

Text #5

Max Range: 3.0111. Min Range: -3.0111

Max Act: 2.7911. Min Act: -0.0000

Data Index: 643036 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 3.0111. Min Range: -3.0111

Max Act: 2.7486. Min Act: -0.0001

Data Index: 575014 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 3.0111. Min Range: -3.0111

Max Act: 2.7221. Min Act: -0.0000

Data Index: 300984 (C4 (Web Text))

Max Activating Token Index: 891

Text #8

Max Range: 3.0111. Min Range: -3.0111

Max Act: 2.7301. Min Act: -0.0000

Data Index: 1477882 (Python Code)

Max Activating Token Index: 327

Text #9

Max Range: 3.0111. Min Range: -3.0111

Max Act: 2.6850. Min Act: -0.0001

Data Index: 982507 (C4 (Web Text))

Max Activating Token Index: 466

Text #10

Max Range: 3.0111. Min Range: -3.0111

Max Act: 2.5280. Min Act: -0.0000

Data Index: 539029 (C4 (Web Text))

Max Activating Token Index: 866

Text #11

Max Range: 3.0111. Min Range: -3.0111

Max Act: 2.5230. Min Act: -0.0001

Data Index: 329700 (C4 (Web Text))

Max Activating Token Index: 722

Text #12

Max Range: 3.0111. Min Range: -3.0111

Max Act: 2.5114. Min Act: -0.0000

Data Index: 17272 (C4 (Web Text))

Max Activating Token Index: 958

Text #13

Max Range: 3.0111. Min Range: -3.0111

Max Act: 2.6469. Min Act: -0.0000

Data Index: 798076 (C4 (Web Text))

Max Activating Token Index: 781

Text #14

Max Range: 3.0111. Min Range: -3.0111

Max Act: 2.6272. Min Act: -0.0001

Data Index: 750434 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 3.0111. Min Range: -3.0111

Max Act: 2.4846. Min Act: -0.0000

Data Index: 1329321 (C4 (Web Text))

Max Activating Token Index: 997

Text #16

Max Range: 3.0111. Min Range: -3.0111

Max Act: 2.6152. Min Act: -0.0000

Data Index: 424412 (C4 (Web Text))

Max Activating Token Index: 830

Text #17

Max Range: 3.0111. Min Range: -3.0111

Max Act: 2.6115. Min Act: -0.0000

Data Index: 657731 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 3.0111. Min Range: -3.0111

Max Act: 2.5902. Min Act: -0.0001

Data Index: 451558 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 3.0111. Min Range: -3.0111

Max Act: 2.5758. Min Act: -0.0000

Data Index: 766819 (C4 (Web Text))

Max Activating Token Index: 309