Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 929 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0898. Min Act: -0.0002

Data Index: 363541 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0740. Min Act: -0.0002

Data Index: 605493 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0716. Min Act: -0.0002

Data Index: 565882 (C4 (Web Text))

Max Activating Token Index: 648

Text #3

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0763. Min Act: -0.0002

Data Index: 1269052 (C4 (Web Text))

Max Activating Token Index: 907

Text #4

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0744. Min Act: -0.0002

Data Index: 977833 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0754. Min Act: -0.0002

Data Index: 1443527 (Python Code)

Max Activating Token Index: 565

Text #6

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0717. Min Act: -0.0002

Data Index: 937471 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0718. Min Act: -0.0002

Data Index: 983672 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0686. Min Act: -0.0002

Data Index: 306736 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0714. Min Act: -0.0002

Data Index: 820012 (C4 (Web Text))

Max Activating Token Index: 767

Text #10

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0718. Min Act: -0.0002

Data Index: 1082538 (C4 (Web Text))

Max Activating Token Index: 726

Text #11

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0663. Min Act: -0.0002

Data Index: 1136461 (C4 (Web Text))

Max Activating Token Index: 682

Text #12

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0730. Min Act: -0.0002

Data Index: 806963 (C4 (Web Text))

Max Activating Token Index: 696

Text #13

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0677. Min Act: -0.0002

Data Index: 1456231 (Python Code)

Max Activating Token Index: 734

Text #14

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0737. Min Act: -0.0002

Data Index: 1349477 (C4 (Web Text))

Max Activating Token Index: 640

Text #15

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0697. Min Act: -0.0002

Data Index: 625628 (C4 (Web Text))

Max Activating Token Index: 860

Text #16

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0709. Min Act: -0.0002

Data Index: 1494141 (Python Code)

Max Activating Token Index: 244

Text #17

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0679. Min Act: -0.0002

Data Index: 396237 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0715. Min Act: -0.0003

Data Index: 1549698 (Python Code)

Max Activating Token Index: 653

Text #19

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0691. Min Act: -0.0002

Data Index: 1409434 (Python Code)

Max Activating Token Index: 431