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

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

Neuron 1817 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1322. Min Act: -0.0001

Data Index: 1378980 (Python Code)

Max Activating Token Index: 24

Text #1

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1056. Min Act: -0.0001

Data Index: 635306 (C4 (Web Text))

Max Activating Token Index: 844

Text #2

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1021. Min Act: -0.0001

Data Index: 823694 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1050. Min Act: -0.0001

Data Index: 409934 (C4 (Web Text))

Max Activating Token Index: 848

Text #4

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0972. Min Act: -0.0001

Data Index: 915021 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0979. Min Act: -0.0001

Data Index: 626619 (C4 (Web Text))

Max Activating Token Index: 998

Text #6

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0909. Min Act: -0.0001

Data Index: 368775 (C4 (Web Text))

Max Activating Token Index: 123

Text #7

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0886. Min Act: -0.0001

Data Index: 1300677 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0906. Min Act: -0.0001

Data Index: 1471285 (Python Code)

Max Activating Token Index: 869

Text #9

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0957. Min Act: -0.0001

Data Index: 1077100 (C4 (Web Text))

Max Activating Token Index: 863

Text #10

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0922. Min Act: -0.0001

Data Index: 838190 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0929. Min Act: -0.0001

Data Index: 290715 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0884. Min Act: -0.0001

Data Index: 714929 (C4 (Web Text))

Max Activating Token Index: 919

Text #13

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0937. Min Act: -0.0001

Data Index: 1277128 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0910. Min Act: -0.0001

Data Index: 1304081 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0842. Min Act: -0.0001

Data Index: 717544 (C4 (Web Text))

Max Activating Token Index: 797

Text #16

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0944. Min Act: -0.0001

Data Index: 383131 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0862. Min Act: -0.0001

Data Index: 1304880 (C4 (Web Text))

Max Activating Token Index: 763

Text #18

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0858. Min Act: -0.0001

Data Index: 113525 (C4 (Web Text))

Max Activating Token Index: 474

Text #19

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0855. Min Act: -0.0001

Data Index: 602709 (C4 (Web Text))

Max Activating Token Index: 882