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

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

Neuron 1153 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0749. Min Act: -0.0002

Data Index: 585379 (C4 (Web Text))

Max Activating Token Index: 495

Text #1

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0674. Min Act: -0.0002

Data Index: 603733 (C4 (Web Text))

Max Activating Token Index: 173

Text #2

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0748. Min Act: -0.0002

Data Index: 1442945 (Python Code)

Max Activating Token Index: 585

Text #3

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0768. Min Act: -0.0002

Data Index: 1317316 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0774. Min Act: -0.0002

Data Index: 1232829 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0805. Min Act: -0.0002

Data Index: 374047 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0705. Min Act: -0.0002

Data Index: 895894 (C4 (Web Text))

Max Activating Token Index: 3

Text #7

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0676. Min Act: -0.0003

Data Index: 1018369 (C4 (Web Text))

Max Activating Token Index: 3

Text #8

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0727. Min Act: -0.0002

Data Index: 101523 (C4 (Web Text))

Max Activating Token Index: 449

Text #9

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0697. Min Act: -0.0002

Data Index: 476357 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0696. Min Act: -0.0003

Data Index: 603557 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0663. Min Act: -0.0002

Data Index: 437129 (C4 (Web Text))

Max Activating Token Index: 441

Text #12

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0690. Min Act: -0.0002

Data Index: 1500843 (Python Code)

Max Activating Token Index: 695

Text #13

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0723. Min Act: -0.0002

Data Index: 566474 (C4 (Web Text))

Max Activating Token Index: 859

Text #14

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0641. Min Act: -0.0002

Data Index: 842325 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0660. Min Act: -0.0002

Data Index: 877771 (C4 (Web Text))

Max Activating Token Index: 746

Text #16

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0687. Min Act: -0.0002

Data Index: 1563952 (Python Code)

Max Activating Token Index: 871

Text #17

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0642. Min Act: -0.0002

Data Index: 690505 (C4 (Web Text))

Max Activating Token Index: 994

Text #18

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0639. Min Act: -0.0002

Data Index: 312013 (C4 (Web Text))

Max Activating Token Index: 248

Text #19

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0665. Min Act: -0.0002

Data Index: 400362 (C4 (Web Text))

Max Activating Token Index: 452