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

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

Neuron 3890 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0603. Min Range: -1.0603

Max Act: 1.0603. Min Act: -0.0000

Data Index: 1044874 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 1.0603. Min Range: -1.0603

Max Act: 1.0492. Min Act: -0.0000

Data Index: 499202 (C4 (Web Text))

Max Activating Token Index: 341

Text #2

Max Range: 1.0603. Min Range: -1.0603

Max Act: 0.9495. Min Act: -0.0000

Data Index: 1336762 (C4 (Web Text))

Max Activating Token Index: 1018

Text #3

Max Range: 1.0603. Min Range: -1.0603

Max Act: 0.9379. Min Act: -0.0000

Data Index: 340027 (C4 (Web Text))

Max Activating Token Index: 833

Text #4

Max Range: 1.0603. Min Range: -1.0603

Max Act: 1.0559. Min Act: -0.0000

Data Index: 1074780 (C4 (Web Text))

Max Activating Token Index: 272

Text #5

Max Range: 1.0603. Min Range: -1.0603

Max Act: 0.9166. Min Act: -0.0000

Data Index: 722092 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 1.0603. Min Range: -1.0603

Max Act: 0.9203. Min Act: -0.0000

Data Index: 563759 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 1.0603. Min Range: -1.0603

Max Act: 0.9072. Min Act: 0.0000

Data Index: 1098356 (C4 (Web Text))

Max Activating Token Index: 690

Text #8

Max Range: 1.0603. Min Range: -1.0603

Max Act: 0.8325. Min Act: -0.0000

Data Index: 823097 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 1.0603. Min Range: -1.0603

Max Act: 0.8299. Min Act: -0.0000

Data Index: 6934 (C4 (Web Text))

Max Activating Token Index: 761

Text #10

Max Range: 1.0603. Min Range: -1.0603

Max Act: 0.8846. Min Act: -0.0000

Data Index: 346614 (C4 (Web Text))

Max Activating Token Index: 647

Text #11

Max Range: 1.0603. Min Range: -1.0603

Max Act: 0.8746. Min Act: -0.0000

Data Index: 100246 (C4 (Web Text))

Max Activating Token Index: 647

Text #12

Max Range: 1.0603. Min Range: -1.0603

Max Act: 0.8107. Min Act: -0.0000

Data Index: 151250 (C4 (Web Text))

Max Activating Token Index: 207

Text #13

Max Range: 1.0603. Min Range: -1.0603

Max Act: 0.7988. Min Act: -0.0000

Data Index: 240591 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 1.0603. Min Range: -1.0603

Max Act: 0.7852. Min Act: -0.0000

Data Index: 787824 (C4 (Web Text))

Max Activating Token Index: 384

Text #15

Max Range: 1.0603. Min Range: -1.0603

Max Act: 0.7850. Min Act: -0.0000

Data Index: 1043952 (C4 (Web Text))

Max Activating Token Index: 718

Text #16

Max Range: 1.0603. Min Range: -1.0603

Max Act: 0.7849. Min Act: -0.0000

Data Index: 791168 (C4 (Web Text))

Max Activating Token Index: 869

Text #17

Max Range: 1.0603. Min Range: -1.0603

Max Act: 0.7689. Min Act: -0.0000

Data Index: 406147 (C4 (Web Text))

Max Activating Token Index: 579

Text #18

Max Range: 1.0603. Min Range: -1.0603

Max Act: 0.7584. Min Act: 0.0000

Data Index: 1197983 (C4 (Web Text))

Max Activating Token Index: 682

Text #19

Max Range: 1.0603. Min Range: -1.0603

Max Act: 0.7564. Min Act: -0.0000

Data Index: 886969 (C4 (Web Text))

Max Activating Token Index: 32