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

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

Neuron 3462 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0850. Min Act: -0.0003

Data Index: 1295086 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0809. Min Act: -0.0003

Data Index: 1095357 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0765. Min Act: -0.0002

Data Index: 391717 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0776. Min Act: -0.0002

Data Index: 973495 (C4 (Web Text))

Max Activating Token Index: 742

Text #4

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0745. Min Act: -0.0002

Data Index: 582837 (C4 (Web Text))

Max Activating Token Index: 464

Text #5

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0745. Min Act: -0.0003

Data Index: 1342708 (C4 (Web Text))

Max Activating Token Index: 262

Text #6

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0726. Min Act: -0.0002

Data Index: 20079 (C4 (Web Text))

Max Activating Token Index: 867

Text #7

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0719. Min Act: -0.0002

Data Index: 1053230 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0719. Min Act: -0.0002

Data Index: 339103 (C4 (Web Text))

Max Activating Token Index: 963

Text #9

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0712. Min Act: -0.0002

Data Index: 143968 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0712. Min Act: -0.0002

Data Index: 1126434 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0678. Min Act: -0.0002

Data Index: 417954 (C4 (Web Text))

Max Activating Token Index: 385

Text #12

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0651. Min Act: -0.0002

Data Index: 23245 (C4 (Web Text))

Max Activating Token Index: 365

Text #13

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0650. Min Act: -0.0002

Data Index: 1202334 (C4 (Web Text))

Max Activating Token Index: 724

Text #14

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0666. Min Act: -0.0002

Data Index: 1197624 (C4 (Web Text))

Max Activating Token Index: 747

Text #15

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0635. Min Act: -0.0002

Data Index: 900239 (C4 (Web Text))

Max Activating Token Index: 811

Text #16

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0613. Min Act: -0.0002

Data Index: 830844 (C4 (Web Text))

Max Activating Token Index: 495

Text #17

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0633. Min Act: -0.0002

Data Index: 164504 (C4 (Web Text))

Max Activating Token Index: 704

Text #18

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0656. Min Act: -0.0002

Data Index: 1131146 (C4 (Web Text))

Max Activating Token Index: 64

Text #19

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0631. Min Act: -0.0002

Data Index: 801433 (C4 (Web Text))

Max Activating Token Index: 967