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

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

Neuron 5858 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: 0.1051. Min Range: -0.1051

Max Act: 0.1051. Min Act: -0.0002

Data Index: 1182949 (C4 (Web Text))

Max Activating Token Index: 464

Text #1

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0959. Min Act: -0.0002

Data Index: 1069814 (C4 (Web Text))

Max Activating Token Index: 868

Text #2

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0873. Min Act: -0.0002

Data Index: 412717 (C4 (Web Text))

Max Activating Token Index: 674

Text #3

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0853. Min Act: -0.0002

Data Index: 494649 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0783. Min Act: -0.0002

Data Index: 96574 (C4 (Web Text))

Max Activating Token Index: 341

Text #5

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0798. Min Act: -0.0002

Data Index: 1005194 (C4 (Web Text))

Max Activating Token Index: 595

Text #6

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0720. Min Act: -0.0002

Data Index: 1351778 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0809. Min Act: -0.0002

Data Index: 1184126 (C4 (Web Text))

Max Activating Token Index: 389

Text #8

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0773. Min Act: -0.0002

Data Index: 2447 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0743. Min Act: -0.0002

Data Index: 1229145 (C4 (Web Text))

Max Activating Token Index: 471

Text #10

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0797. Min Act: -0.0002

Data Index: 536669 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0767. Min Act: -0.0002

Data Index: 327952 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0762. Min Act: -0.0002

Data Index: 514486 (C4 (Web Text))

Max Activating Token Index: 833

Text #13

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0722. Min Act: -0.0002

Data Index: 201398 (C4 (Web Text))

Max Activating Token Index: 406

Text #14

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0725. Min Act: -0.0002

Data Index: 1344621 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0747. Min Act: -0.0002

Data Index: 944737 (C4 (Web Text))

Max Activating Token Index: 612

Text #16

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0694. Min Act: -0.0002

Data Index: 512305 (C4 (Web Text))

Max Activating Token Index: 288

Text #17

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0721. Min Act: -0.0002

Data Index: 67142 (C4 (Web Text))

Max Activating Token Index: 442

Text #18

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0718. Min Act: -0.0002

Data Index: 350867 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0742. Min Act: -0.0002

Data Index: 275376 (C4 (Web Text))

Max Activating Token Index: 12