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

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

Neuron 2695 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0838. Min Act: -0.0001

Data Index: 492572 (C4 (Web Text))

Max Activating Token Index: 632

Text #1

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0767. Min Act: -0.0002

Data Index: 791078 (C4 (Web Text))

Max Activating Token Index: 869

Text #2

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0685. Min Act: -0.0002

Data Index: 426161 (C4 (Web Text))

Max Activating Token Index: 953

Text #3

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0738. Min Act: -0.0002

Data Index: 37665 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0697. Min Act: -0.0002

Data Index: 630960 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0689. Min Act: -0.0002

Data Index: 367803 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0682. Min Act: -0.0002

Data Index: 896179 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0679. Min Act: -0.0002

Data Index: 502472 (C4 (Web Text))

Max Activating Token Index: 586

Text #8

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0674. Min Act: -0.0002

Data Index: 642957 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0674. Min Act: -0.0002

Data Index: 80984 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0660. Min Act: -0.0002

Data Index: 1655296 (Python Code)

Max Activating Token Index: 200

Text #11

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0659. Min Act: -0.0002

Data Index: 401706 (C4 (Web Text))

Max Activating Token Index: 600

Text #12

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0659. Min Act: -0.0001

Data Index: 1000733 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0642. Min Act: -0.0002

Data Index: 1464724 (Python Code)

Max Activating Token Index: 7

Text #14

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0642. Min Act: -0.0001

Data Index: 905070 (C4 (Web Text))

Max Activating Token Index: 109

Text #15

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0638. Min Act: -0.0002

Data Index: 841268 (C4 (Web Text))

Max Activating Token Index: 284

Text #16

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0636. Min Act: -0.0002

Data Index: 634371 (C4 (Web Text))

Max Activating Token Index: 805

Text #17

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0632. Min Act: -0.0002

Data Index: 35014 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0628. Min Act: -0.0001

Data Index: 1073234 (C4 (Web Text))

Max Activating Token Index: 176

Text #19

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0622. Min Act: -0.0002

Data Index: 917429 (C4 (Web Text))

Max Activating Token Index: 46