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

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

Neuron 1063 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0862. Min Act: -0.0003

Data Index: 239911 (C4 (Web Text))

Max Activating Token Index: 539

Text #1

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0778. Min Act: -0.0003

Data Index: 561060 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0865. Min Act: -0.0003

Data Index: 855385 (C4 (Web Text))

Max Activating Token Index: 543

Text #3

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0804. Min Act: -0.0003

Data Index: 1198677 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0748. Min Act: -0.0003

Data Index: 1479006 (Python Code)

Max Activating Token Index: 834

Text #5

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0729. Min Act: -0.0003

Data Index: 1503011 (Python Code)

Max Activating Token Index: 799

Text #6

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0738. Min Act: -0.0003

Data Index: 1258610 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0704. Min Act: -0.0003

Data Index: 752963 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0697. Min Act: -0.0003

Data Index: 646471 (C4 (Web Text))

Max Activating Token Index: 913

Text #9

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0682. Min Act: -0.0003

Data Index: 1608598 (Python Code)

Max Activating Token Index: 142

Text #10

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0673. Min Act: -0.0003

Data Index: 1405376 (Python Code)

Max Activating Token Index: 746

Text #11

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0658. Min Act: -0.0003

Data Index: 1454740 (Python Code)

Max Activating Token Index: 848

Text #12

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0635. Min Act: -0.0003

Data Index: 1079182 (C4 (Web Text))

Max Activating Token Index: 271

Text #13

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0685. Min Act: -0.0003

Data Index: 794201 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0659. Min Act: -0.0003

Data Index: 1383600 (Python Code)

Max Activating Token Index: 507

Text #15

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0671. Min Act: -0.0003

Data Index: 725647 (C4 (Web Text))

Max Activating Token Index: 448

Text #16

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0647. Min Act: -0.0003

Data Index: 1370838 (Python Code)

Max Activating Token Index: 862

Text #17

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0652. Min Act: -0.0003

Data Index: 721941 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0650. Min Act: -0.0003

Data Index: 1140825 (C4 (Web Text))

Max Activating Token Index: 602

Text #19

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0659. Min Act: -0.0003

Data Index: 1617578 (Python Code)

Max Activating Token Index: 942