Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2010 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0791. Min Act: -0.0001

Data Index: 1286033 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0838. Min Act: -0.0002

Data Index: 532247 (C4 (Web Text))

Max Activating Token Index: 914

Text #2

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0794. Min Act: -0.0002

Data Index: 573258 (C4 (Web Text))

Max Activating Token Index: 780

Text #3

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0786. Min Act: -0.0002

Data Index: 539715 (C4 (Web Text))

Max Activating Token Index: 554

Text #4

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0783. Min Act: -0.0001

Data Index: 970799 (C4 (Web Text))

Max Activating Token Index: 607

Text #5

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0751. Min Act: -0.0001

Data Index: 1095616 (C4 (Web Text))

Max Activating Token Index: 667

Text #6

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0768. Min Act: -0.0002

Data Index: 128238 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0769. Min Act: -0.0002

Data Index: 165876 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0735. Min Act: -0.0002

Data Index: 933389 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0759. Min Act: -0.0002

Data Index: 716716 (C4 (Web Text))

Max Activating Token Index: 703

Text #10

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0702. Min Act: -0.0002

Data Index: 122338 (C4 (Web Text))

Max Activating Token Index: 879

Text #11

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0732. Min Act: -0.0001

Data Index: 591397 (C4 (Web Text))

Max Activating Token Index: 922

Text #12

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0692. Min Act: -0.0002

Data Index: 40476 (C4 (Web Text))

Max Activating Token Index: 355

Text #13

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0743. Min Act: -0.0001

Data Index: 183167 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0727. Min Act: -0.0001

Data Index: 1228279 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0723. Min Act: -0.0001

Data Index: 970285 (C4 (Web Text))

Max Activating Token Index: 548

Text #16

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0691. Min Act: -0.0002

Data Index: 890246 (C4 (Web Text))

Max Activating Token Index: 629

Text #17

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0742. Min Act: -0.0002

Data Index: 524744 (C4 (Web Text))

Max Activating Token Index: 280

Text #18

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0715. Min Act: -0.0002

Data Index: 1099448 (C4 (Web Text))

Max Activating Token Index: 576

Text #19

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0770. Min Act: -0.0002

Data Index: 84749 (C4 (Web Text))

Max Activating Token Index: 576