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

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

Neuron 5330 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: 0.0902. Min Range: -0.0902

Max Act: 0.0690. Min Act: -0.0002

Data Index: 888390 (C4 (Web Text))

Max Activating Token Index: 859

Text #1

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0902. Min Act: -0.0001

Data Index: 1263071 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0854. Min Act: -0.0001

Data Index: 378589 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0724. Min Act: -0.0001

Data Index: 128653 (C4 (Web Text))

Max Activating Token Index: 311

Text #4

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0898. Min Act: -0.0001

Data Index: 432625 (C4 (Web Text))

Max Activating Token Index: 259

Text #5

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0901. Min Act: -0.0001

Data Index: 885098 (C4 (Web Text))

Max Activating Token Index: 926

Text #6

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0855. Min Act: -0.0001

Data Index: 420349 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0871. Min Act: -0.0001

Data Index: 1038793 (C4 (Web Text))

Max Activating Token Index: 256

Text #8

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0716. Min Act: -0.0001

Data Index: 960050 (C4 (Web Text))

Max Activating Token Index: 134

Text #9

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0772. Min Act: -0.0001

Data Index: 241632 (C4 (Web Text))

Max Activating Token Index: 958

Text #10

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0835. Min Act: -0.0001

Data Index: 910993 (C4 (Web Text))

Max Activating Token Index: 425

Text #11

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0773. Min Act: -0.0001

Data Index: 813510 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0660. Min Act: -0.0001

Data Index: 457911 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0762. Min Act: -0.0001

Data Index: 1350678 (C4 (Web Text))

Max Activating Token Index: 54

Text #14

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0707. Min Act: -0.0001

Data Index: 842841 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0853. Min Act: -0.0001

Data Index: 67693 (C4 (Web Text))

Max Activating Token Index: 190

Text #16

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0615. Min Act: -0.0001

Data Index: 577946 (C4 (Web Text))

Max Activating Token Index: 688

Text #17

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0779. Min Act: -0.0001

Data Index: 943531 (C4 (Web Text))

Max Activating Token Index: 45

Text #18

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0725. Min Act: -0.0001

Data Index: 642919 (C4 (Web Text))

Max Activating Token Index: 628

Text #19

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0774. Min Act: -0.0001

Data Index: 940622 (C4 (Web Text))

Max Activating Token Index: 158