Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 230 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0794. Min Act: -0.0001

Data Index: 81429 (C4 (Web Text))

Max Activating Token Index: 881

Text #1

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0785. Min Act: -0.0001

Data Index: 1009984 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0697. Min Act: -0.0001

Data Index: 901137 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0723. Min Act: -0.0001

Data Index: 265796 (C4 (Web Text))

Max Activating Token Index: 699

Text #4

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0727. Min Act: -0.0001

Data Index: 556078 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0738. Min Act: -0.0001

Data Index: 22239 (C4 (Web Text))

Max Activating Token Index: 720

Text #6

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0717. Min Act: -0.0001

Data Index: 288086 (C4 (Web Text))

Max Activating Token Index: 714

Text #7

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0689. Min Act: -0.0001

Data Index: 349285 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0593. Min Act: -0.0001

Data Index: 1316 (C4 (Web Text))

Max Activating Token Index: 627

Text #9

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0720. Min Act: -0.0001

Data Index: 300832 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0699. Min Act: -0.0001

Data Index: 1058886 (C4 (Web Text))

Max Activating Token Index: 238

Text #11

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0708. Min Act: -0.0001

Data Index: 1628499 (Python Code)

Max Activating Token Index: 937

Text #12

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0692. Min Act: -0.0001

Data Index: 654592 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0680. Min Act: -0.0001

Data Index: 481430 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0633. Min Act: -0.0001

Data Index: 151230 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0673. Min Act: -0.0001

Data Index: 721393 (C4 (Web Text))

Max Activating Token Index: 410

Text #16

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0658. Min Act: -0.0001

Data Index: 70806 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0680. Min Act: -0.0001

Data Index: 693229 (C4 (Web Text))

Max Activating Token Index: 311

Text #18

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0675. Min Act: -0.0001

Data Index: 390014 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0643. Min Act: -0.0001

Data Index: 602738 (C4 (Web Text))

Max Activating Token Index: 422