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

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

Neuron 3 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0905. Min Act: -0.0001

Data Index: 276374 (C4 (Web Text))

Max Activating Token Index: 926

Text #1

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0809. Min Act: -0.0001

Data Index: 755515 (C4 (Web Text))

Max Activating Token Index: 554

Text #2

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0593. Min Act: -0.0001

Data Index: 1067337 (C4 (Web Text))

Max Activating Token Index: 834

Text #3

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0722. Min Act: -0.0001

Data Index: 975433 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0684. Min Act: -0.0001

Data Index: 870483 (C4 (Web Text))

Max Activating Token Index: 865

Text #5

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0761. Min Act: -0.0001

Data Index: 94702 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0812. Min Act: -0.0001

Data Index: 91329 (C4 (Web Text))

Max Activating Token Index: 721

Text #7

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0704. Min Act: -0.0001

Data Index: 1075487 (C4 (Web Text))

Max Activating Token Index: 550

Text #8

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0636. Min Act: -0.0001

Data Index: 559825 (C4 (Web Text))

Max Activating Token Index: 611

Text #9

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0698. Min Act: -0.0001

Data Index: 155773 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0718. Min Act: -0.0001

Data Index: 562453 (C4 (Web Text))

Max Activating Token Index: 592

Text #11

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0681. Min Act: -0.0001

Data Index: 15506 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0726. Min Act: -0.0001

Data Index: 1264718 (C4 (Web Text))

Max Activating Token Index: 358

Text #13

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0688. Min Act: -0.0001

Data Index: 872258 (C4 (Web Text))

Max Activating Token Index: 505

Text #14

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0749. Min Act: -0.0001

Data Index: 1068567 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0644. Min Act: -0.0001

Data Index: 891579 (C4 (Web Text))

Max Activating Token Index: 479

Text #16

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0686. Min Act: -0.0001

Data Index: 395871 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0685. Min Act: -0.0001

Data Index: 539064 (C4 (Web Text))

Max Activating Token Index: 356

Text #18

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0603. Min Act: -0.0001

Data Index: 728144 (C4 (Web Text))

Max Activating Token Index: 947

Text #19

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0688. Min Act: -0.0001

Data Index: 1214912 (C4 (Web Text))

Max Activating Token Index: 704