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

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

Neuron 3782 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1149. Min Act: -0.0000

Data Index: 974135 (C4 (Web Text))

Max Activating Token Index: 790

Text #1

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1253. Min Act: -0.0000

Data Index: 473370 (C4 (Web Text))

Max Activating Token Index: 156

Text #2

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1238. Min Act: -0.0000

Data Index: 526112 (C4 (Web Text))

Max Activating Token Index: 887

Text #3

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1153. Min Act: -0.0000

Data Index: 1098564 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1073. Min Act: -0.0000

Data Index: 134902 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0888. Min Act: -0.0000

Data Index: 925180 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0795. Min Act: -0.0000

Data Index: 974780 (C4 (Web Text))

Max Activating Token Index: 857

Text #7

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0847. Min Act: -0.0000

Data Index: 1313930 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0786. Min Act: -0.0000

Data Index: 1021245 (C4 (Web Text))

Max Activating Token Index: 788

Text #9

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0814. Min Act: -0.0000

Data Index: 627806 (C4 (Web Text))

Max Activating Token Index: 884

Text #10

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0766. Min Act: -0.0000

Data Index: 550306 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0744. Min Act: -0.0000

Data Index: 551116 (C4 (Web Text))

Max Activating Token Index: 981

Text #12

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0696. Min Act: -0.0000

Data Index: 1330337 (C4 (Web Text))

Max Activating Token Index: 344

Text #13

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0722. Min Act: -0.0000

Data Index: 720604 (C4 (Web Text))

Max Activating Token Index: 869

Text #14

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0749. Min Act: -0.0000

Data Index: 413911 (C4 (Web Text))

Max Activating Token Index: 594

Text #15

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0773. Min Act: -0.0000

Data Index: 1237833 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0773. Min Act: -0.0000

Data Index: 1301240 (C4 (Web Text))

Max Activating Token Index: 252

Text #17

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0794. Min Act: -0.0000

Data Index: 1337184 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0684. Min Act: -0.0000

Data Index: 359884 (C4 (Web Text))

Max Activating Token Index: 677

Text #19

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0506. Min Act: -0.0000

Data Index: 709154 (C4 (Web Text))

Max Activating Token Index: 564