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

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

Neuron 2890 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7384. Min Range: -2.7384

Max Act: 2.7384. Min Act: -0.0000

Data Index: 550218 (C4 (Web Text))

Max Activating Token Index: 641

Text #1

Max Range: 2.7384. Min Range: -2.7384

Max Act: 2.7288. Min Act: -0.0000

Data Index: 563865 (C4 (Web Text))

Max Activating Token Index: 652

Text #2

Max Range: 2.7384. Min Range: -2.7384

Max Act: 2.5839. Min Act: -0.0000

Data Index: 368424 (C4 (Web Text))

Max Activating Token Index: 667

Text #3

Max Range: 2.7384. Min Range: -2.7384

Max Act: 2.5326. Min Act: -0.0000

Data Index: 1581268 (Python Code)

Max Activating Token Index: 30

Text #4

Max Range: 2.7384. Min Range: -2.7384

Max Act: 2.4801. Min Act: -0.0000

Data Index: 972756 (C4 (Web Text))

Max Activating Token Index: 444

Text #5

Max Range: 2.7384. Min Range: -2.7384

Max Act: 2.4579. Min Act: -0.0000

Data Index: 1371481 (Python Code)

Max Activating Token Index: 117

Text #6

Max Range: 2.7384. Min Range: -2.7384

Max Act: 2.0915. Min Act: -0.0000

Data Index: 61652 (C4 (Web Text))

Max Activating Token Index: 695

Text #7

Max Range: 2.7384. Min Range: -2.7384

Max Act: 2.0870. Min Act: -0.0000

Data Index: 1027567 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 2.7384. Min Range: -2.7384

Max Act: 2.0832. Min Act: -0.0000

Data Index: 1162964 (C4 (Web Text))

Max Activating Token Index: 863

Text #9

Max Range: 2.7384. Min Range: -2.7384

Max Act: 2.0603. Min Act: -0.0000

Data Index: 1474586 (Python Code)

Max Activating Token Index: 714

Text #10

Max Range: 2.7384. Min Range: -2.7384

Max Act: 2.0588. Min Act: -0.0000

Data Index: 1519038 (Python Code)

Max Activating Token Index: 673

Text #11

Max Range: 2.7384. Min Range: -2.7384

Max Act: 1.8807. Min Act: -0.0000

Data Index: 72612 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 2.7384. Min Range: -2.7384

Max Act: 1.9633. Min Act: -0.0000

Data Index: 981412 (C4 (Web Text))

Max Activating Token Index: 905

Text #13

Max Range: 2.7384. Min Range: -2.7384

Max Act: 1.9645. Min Act: -0.0000

Data Index: 1306173 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 2.7384. Min Range: -2.7384

Max Act: 1.9753. Min Act: -0.0000

Data Index: 906495 (C4 (Web Text))

Max Activating Token Index: 864

Text #15

Max Range: 2.7384. Min Range: -2.7384

Max Act: 1.9693. Min Act: -0.0000

Data Index: 1410089 (Python Code)

Max Activating Token Index: 670

Text #16

Max Range: 2.7384. Min Range: -2.7384

Max Act: 1.9636. Min Act: -0.0000

Data Index: 604705 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 2.7384. Min Range: -2.7384

Max Act: 1.8462. Min Act: -0.0000

Data Index: 26332 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 2.7384. Min Range: -2.7384

Max Act: 1.9584. Min Act: -0.0000

Data Index: 760533 (C4 (Web Text))

Max Activating Token Index: 871

Text #19

Max Range: 2.7384. Min Range: -2.7384

Max Act: 1.9349. Min Act: -0.0000

Data Index: 820312 (C4 (Web Text))

Max Activating Token Index: 978