Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 629 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1940. Min Act: -0.0001

Data Index: 1280805 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1999. Min Act: -0.0001

Data Index: 265558 (C4 (Web Text))

Max Activating Token Index: 625

Text #2

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1823. Min Act: -0.0001

Data Index: 1196789 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1786. Min Act: -0.0001

Data Index: 893747 (C4 (Web Text))

Max Activating Token Index: 294

Text #4

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1916. Min Act: -0.0001

Data Index: 935016 (C4 (Web Text))

Max Activating Token Index: 6

Text #5

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1838. Min Act: -0.0001

Data Index: 451576 (C4 (Web Text))

Max Activating Token Index: 684

Text #6

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1749. Min Act: -0.0001

Data Index: 217592 (C4 (Web Text))

Max Activating Token Index: 844

Text #7

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1812. Min Act: -0.0001

Data Index: 629389 (C4 (Web Text))

Max Activating Token Index: 736

Text #8

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1812. Min Act: -0.0001

Data Index: 1263664 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1857. Min Act: -0.0001

Data Index: 382856 (C4 (Web Text))

Max Activating Token Index: 729

Text #10

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1896. Min Act: -0.0001

Data Index: 727701 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1850. Min Act: -0.0001

Data Index: 55721 (C4 (Web Text))

Max Activating Token Index: 641

Text #12

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1786. Min Act: -0.0001

Data Index: 977223 (C4 (Web Text))

Max Activating Token Index: 440

Text #13

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1748. Min Act: -0.0001

Data Index: 781689 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1759. Min Act: -0.0001

Data Index: 105361 (C4 (Web Text))

Max Activating Token Index: 389

Text #15

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1812. Min Act: -0.0001

Data Index: 984581 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1688. Min Act: -0.0001

Data Index: 551324 (C4 (Web Text))

Max Activating Token Index: 90

Text #17

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1634. Min Act: -0.0001

Data Index: 1344424 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1666. Min Act: -0.0001

Data Index: 918691 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1636. Min Act: -0.0001

Data Index: 417761 (C4 (Web Text))

Max Activating Token Index: 920