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

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

Neuron 1943 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: 0.1300. Min Range: -0.1300

Max Act: 0.1272. Min Act: -0.0002

Data Index: 1490267 (Python Code)

Max Activating Token Index: 106

Text #1

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1300. Min Act: -0.0002

Data Index: 1388946 (Python Code)

Max Activating Token Index: 865

Text #2

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1209. Min Act: -0.0002

Data Index: 1394597 (Python Code)

Max Activating Token Index: 116

Text #3

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1064. Min Act: -0.0002

Data Index: 1638012 (Python Code)

Max Activating Token Index: 39

Text #4

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1039. Min Act: -0.0002

Data Index: 1468557 (Python Code)

Max Activating Token Index: 239

Text #5

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.0948. Min Act: -0.0002

Data Index: 1404778 (Python Code)

Max Activating Token Index: 387

Text #6

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.0954. Min Act: -0.0002

Data Index: 1451374 (Python Code)

Max Activating Token Index: 106

Text #7

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.0931. Min Act: -0.0002

Data Index: 1609521 (Python Code)

Max Activating Token Index: 648

Text #8

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.0911. Min Act: -0.0002

Data Index: 1475238 (Python Code)

Max Activating Token Index: 134

Text #9

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.0893. Min Act: -0.0002

Data Index: 1415117 (Python Code)

Max Activating Token Index: 630

Text #10

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.0920. Min Act: -0.0002

Data Index: 1422673 (Python Code)

Max Activating Token Index: 239

Text #11

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.0846. Min Act: -0.0002

Data Index: 1451043 (Python Code)

Max Activating Token Index: 953

Text #12

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.0826. Min Act: -0.0002

Data Index: 1447548 (Python Code)

Max Activating Token Index: 844

Text #13

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.0829. Min Act: -0.0002

Data Index: 1376133 (Python Code)

Max Activating Token Index: 773

Text #14

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.0814. Min Act: -0.0002

Data Index: 1443572 (Python Code)

Max Activating Token Index: 731

Text #15

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.0810. Min Act: -0.0002

Data Index: 851386 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.0801. Min Act: -0.0002

Data Index: 1569257 (Python Code)

Max Activating Token Index: 389

Text #17

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.0800. Min Act: -0.0002

Data Index: 1442759 (Python Code)

Max Activating Token Index: 20

Text #18

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.0823. Min Act: -0.0002

Data Index: 1521654 (Python Code)

Max Activating Token Index: 894

Text #19

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.0764. Min Act: -0.0002

Data Index: 1581223 (Python Code)

Max Activating Token Index: 639