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

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

Neuron 4313 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: 0.0951. Min Range: -0.0951

Max Act: 0.0951. Min Act: -0.0002

Data Index: 939666 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0888. Min Act: -0.0002

Data Index: 1622851 (Python Code)

Max Activating Token Index: 225

Text #2

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0873. Min Act: -0.0002

Data Index: 1551658 (Python Code)

Max Activating Token Index: 941

Text #3

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0863. Min Act: -0.0002

Data Index: 1503890 (Python Code)

Max Activating Token Index: 506

Text #4

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0847. Min Act: -0.0002

Data Index: 787853 (C4 (Web Text))

Max Activating Token Index: 525

Text #5

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0797. Min Act: -0.0002

Data Index: 397132 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0786. Min Act: -0.0002

Data Index: 647263 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0786. Min Act: -0.0002

Data Index: 1338073 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0748. Min Act: -0.0002

Data Index: 1413516 (Python Code)

Max Activating Token Index: 306

Text #9

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0759. Min Act: -0.0002

Data Index: 1546975 (Python Code)

Max Activating Token Index: 874

Text #10

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0785. Min Act: -0.0002

Data Index: 1384589 (Python Code)

Max Activating Token Index: 869

Text #11

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0751. Min Act: -0.0002

Data Index: 225276 (C4 (Web Text))

Max Activating Token Index: 1013

Text #12

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0751. Min Act: -0.0002

Data Index: 897872 (C4 (Web Text))

Max Activating Token Index: 387

Text #13

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0773. Min Act: -0.0002

Data Index: 1194653 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0739. Min Act: -0.0002

Data Index: 1567188 (Python Code)

Max Activating Token Index: 155

Text #15

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0744. Min Act: -0.0002

Data Index: 422965 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0710. Min Act: -0.0002

Data Index: 230978 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0758. Min Act: -0.0002

Data Index: 1640976 (Python Code)

Max Activating Token Index: 584

Text #18

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0701. Min Act: -0.0002

Data Index: 918717 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0698. Min Act: -0.0002

Data Index: 1614208 (Python Code)

Max Activating Token Index: 66