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

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

Neuron 3553 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0913. Min Act: -0.0002

Data Index: 1132794 (C4 (Web Text))

Max Activating Token Index: 410

Text #1

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0877. Min Act: -0.0002

Data Index: 214048 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0848. Min Act: -0.0002

Data Index: 583844 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0817. Min Act: -0.0003

Data Index: 424636 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0800. Min Act: -0.0003

Data Index: 1193701 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0813. Min Act: -0.0002

Data Index: 1074057 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0778. Min Act: -0.0003

Data Index: 517166 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0772. Min Act: -0.0003

Data Index: 1353018 (C4 (Web Text))

Max Activating Token Index: 867

Text #8

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0770. Min Act: -0.0003

Data Index: 935699 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0744. Min Act: -0.0003

Data Index: 1132811 (C4 (Web Text))

Max Activating Token Index: 622

Text #10

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0755. Min Act: -0.0002

Data Index: 146770 (C4 (Web Text))

Max Activating Token Index: 566

Text #11

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0715. Min Act: -0.0002

Data Index: 1420045 (Python Code)

Max Activating Token Index: 196

Text #12

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0722. Min Act: -0.0002

Data Index: 1021048 (C4 (Web Text))

Max Activating Token Index: 188

Text #13

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0706. Min Act: -0.0002

Data Index: 733276 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0688. Min Act: -0.0002

Data Index: 196501 (C4 (Web Text))

Max Activating Token Index: 511

Text #15

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0735. Min Act: -0.0003

Data Index: 409739 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0697. Min Act: -0.0003

Data Index: 606422 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0723. Min Act: -0.0002

Data Index: 418045 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0686. Min Act: -0.0002

Data Index: 1365895 (Python Code)

Max Activating Token Index: 597

Text #19

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0679. Min Act: -0.0002

Data Index: 122243 (C4 (Web Text))

Max Activating Token Index: 654