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

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

Neuron 1940 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1918. Min Act: -0.0001

Data Index: 554128 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.2086. Min Act: -0.0001

Data Index: 1262122 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1969. Min Act: -0.0001

Data Index: 1134334 (C4 (Web Text))

Max Activating Token Index: 706

Text #3

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1809. Min Act: -0.0001

Data Index: 803973 (C4 (Web Text))

Max Activating Token Index: 844

Text #4

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1828. Min Act: -0.0001

Data Index: 49432 (C4 (Web Text))

Max Activating Token Index: 714

Text #5

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1821. Min Act: -0.0001

Data Index: 1101924 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1910. Min Act: -0.0001

Data Index: 340510 (C4 (Web Text))

Max Activating Token Index: 935

Text #7

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1805. Min Act: -0.0001

Data Index: 244636 (C4 (Web Text))

Max Activating Token Index: 748

Text #8

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1784. Min Act: -0.0001

Data Index: 405539 (C4 (Web Text))

Max Activating Token Index: 584

Text #9

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1721. Min Act: -0.0001

Data Index: 434344 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1776. Min Act: -0.0001

Data Index: 1212615 (C4 (Web Text))

Max Activating Token Index: 799

Text #11

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1692. Min Act: -0.0001

Data Index: 332295 (C4 (Web Text))

Max Activating Token Index: 976

Text #12

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1649. Min Act: -0.0001

Data Index: 628822 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1744. Min Act: -0.0001

Data Index: 961386 (C4 (Web Text))

Max Activating Token Index: 486

Text #14

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1633. Min Act: -0.0001

Data Index: 578259 (C4 (Web Text))

Max Activating Token Index: 962

Text #15

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1602. Min Act: -0.0001

Data Index: 304862 (C4 (Web Text))

Max Activating Token Index: 916

Text #16

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1684. Min Act: -0.0001

Data Index: 1261673 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1634. Min Act: -0.0001

Data Index: 484257 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1656. Min Act: -0.0001

Data Index: 1305229 (C4 (Web Text))

Max Activating Token Index: 804

Text #19

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1555. Min Act: -0.0001

Data Index: 148805 (C4 (Web Text))

Max Activating Token Index: 926