Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3897 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0745. Min Act: -0.0002

Data Index: 632172 (C4 (Web Text))

Max Activating Token Index: 580

Text #1

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0769. Min Act: -0.0002

Data Index: 68666 (C4 (Web Text))

Max Activating Token Index: 99

Text #2

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0767. Min Act: -0.0002

Data Index: 323202 (C4 (Web Text))

Max Activating Token Index: 286

Text #3

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0734. Min Act: -0.0002

Data Index: 741846 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0731. Min Act: -0.0002

Data Index: 1336911 (C4 (Web Text))

Max Activating Token Index: 826

Text #5

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0711. Min Act: -0.0002

Data Index: 891155 (C4 (Web Text))

Max Activating Token Index: 436

Text #6

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0658. Min Act: -0.0002

Data Index: 821437 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0647. Min Act: -0.0002

Data Index: 679360 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0671. Min Act: -0.0002

Data Index: 1337829 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0646. Min Act: -0.0002

Data Index: 163898 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0630. Min Act: -0.0002

Data Index: 348884 (C4 (Web Text))

Max Activating Token Index: 318

Text #11

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0619. Min Act: -0.0002

Data Index: 1322017 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0617. Min Act: -0.0002

Data Index: 515554 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0633. Min Act: -0.0002

Data Index: 534946 (C4 (Web Text))

Max Activating Token Index: 978

Text #14

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0575. Min Act: -0.0002

Data Index: 362686 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0614. Min Act: -0.0002

Data Index: 701439 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0571. Min Act: -0.0002

Data Index: 1148991 (C4 (Web Text))

Max Activating Token Index: 588

Text #17

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0591. Min Act: -0.0002

Data Index: 845453 (C4 (Web Text))

Max Activating Token Index: 155

Text #18

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0609. Min Act: -0.0002

Data Index: 1329877 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0586. Min Act: -0.0002

Data Index: 1147879 (C4 (Web Text))

Max Activating Token Index: 212