Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 884 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0918. Min Act: -0.0003

Data Index: 199092 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0861. Min Act: -0.0004

Data Index: 127752 (C4 (Web Text))

Max Activating Token Index: 659

Text #2

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0852. Min Act: -0.0003

Data Index: 888865 (C4 (Web Text))

Max Activating Token Index: 579

Text #3

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0832. Min Act: -0.0003

Data Index: 939995 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0804. Min Act: -0.0003

Data Index: 159743 (C4 (Web Text))

Max Activating Token Index: 485

Text #5

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0783. Min Act: -0.0003

Data Index: 827085 (C4 (Web Text))

Max Activating Token Index: 284

Text #6

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0759. Min Act: -0.0003

Data Index: 334739 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0782. Min Act: -0.0003

Data Index: 47450 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0757. Min Act: -0.0003

Data Index: 199505 (C4 (Web Text))

Max Activating Token Index: 481

Text #9

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0722. Min Act: -0.0003

Data Index: 31839 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0747. Min Act: -0.0004

Data Index: 535017 (C4 (Web Text))

Max Activating Token Index: 736

Text #11

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0730. Min Act: -0.0004

Data Index: 85365 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0758. Min Act: -0.0003

Data Index: 501633 (C4 (Web Text))

Max Activating Token Index: 343

Text #13

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0750. Min Act: -0.0003

Data Index: 232548 (C4 (Web Text))

Max Activating Token Index: 611

Text #14

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0723. Min Act: -0.0003

Data Index: 402774 (C4 (Web Text))

Max Activating Token Index: 351

Text #15

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0720. Min Act: -0.0003

Data Index: 319060 (C4 (Web Text))

Max Activating Token Index: 821

Text #16

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0737. Min Act: -0.0003

Data Index: 1146479 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0694. Min Act: -0.0004

Data Index: 949576 (C4 (Web Text))

Max Activating Token Index: 528

Text #18

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0730. Min Act: -0.0003

Data Index: 518940 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0737. Min Act: -0.0003

Data Index: 72920 (C4 (Web Text))

Max Activating Token Index: 658