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

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

Neuron 522 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: 0.0848. Min Range: -0.0848

Max Act: 0.0848. Min Act: 0.0001

Data Index: 809706 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0835. Min Act: -0.0003

Data Index: 895453 (C4 (Web Text))

Max Activating Token Index: 103

Text #2

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0776. Min Act: -0.0004

Data Index: 393822 (C4 (Web Text))

Max Activating Token Index: 589

Text #3

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0750. Min Act: -0.0004

Data Index: 28647 (C4 (Web Text))

Max Activating Token Index: 817

Text #4

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0732. Min Act: -0.0002

Data Index: 239857 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0738. Min Act: -0.0002

Data Index: 428371 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0724. Min Act: -0.0002

Data Index: 398194 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0719. Min Act: -0.0002

Data Index: 826862 (C4 (Web Text))

Max Activating Token Index: 584

Text #8

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0719. Min Act: -0.0002

Data Index: 1229738 (C4 (Web Text))

Max Activating Token Index: 973

Text #9

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0733. Min Act: -0.0003

Data Index: 1166858 (C4 (Web Text))

Max Activating Token Index: 839

Text #10

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0716. Min Act: 0.0001

Data Index: 806066 (C4 (Web Text))

Max Activating Token Index: 411

Text #11

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0741. Min Act: -0.0003

Data Index: 1015493 (C4 (Web Text))

Max Activating Token Index: 977

Text #12

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0718. Min Act: 0.0001

Data Index: 847896 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0716. Min Act: -0.0002

Data Index: 1101395 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0697. Min Act: -0.0002

Data Index: 859230 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0708. Min Act: 0.0001

Data Index: 863025 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0706. Min Act: 0.0000

Data Index: 821131 (C4 (Web Text))

Max Activating Token Index: 845

Text #17

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0702. Min Act: -0.0000

Data Index: 1325519 (C4 (Web Text))

Max Activating Token Index: 838

Text #18

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0682. Min Act: -0.0004

Data Index: 589119 (C4 (Web Text))

Max Activating Token Index: 878

Text #19

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0683. Min Act: 0.0001

Data Index: 1263136 (C4 (Web Text))

Max Activating Token Index: 291