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

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

Neuron 3383 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: 0.1528. Min Range: -0.1528

Max Act: 0.1528. Min Act: -0.0001

Data Index: 1471809 (Python Code)

Max Activating Token Index: 8

Text #1

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1237. Min Act: -0.0001

Data Index: 1421927 (Python Code)

Max Activating Token Index: 36

Text #2

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1203. Min Act: -0.0001

Data Index: 1527284 (Python Code)

Max Activating Token Index: 44

Text #3

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1119. Min Act: -0.0001

Data Index: 1416298 (Python Code)

Max Activating Token Index: 16

Text #4

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0928. Min Act: -0.0001

Data Index: 1557010 (Python Code)

Max Activating Token Index: 20

Text #5

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0874. Min Act: -0.0001

Data Index: 535577 (C4 (Web Text))

Max Activating Token Index: 8

Text #6

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0898. Min Act: -0.0001

Data Index: 1373364 (Python Code)

Max Activating Token Index: 14

Text #7

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0890. Min Act: -0.0001

Data Index: 1527712 (Python Code)

Max Activating Token Index: 4

Text #8

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0871. Min Act: -0.0001

Data Index: 1508101 (Python Code)

Max Activating Token Index: 4

Text #9

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0832. Min Act: -0.0001

Data Index: 798469 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0824. Min Act: -0.0001

Data Index: 1401241 (Python Code)

Max Activating Token Index: 11

Text #11

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0811. Min Act: -0.0001

Data Index: 1414587 (Python Code)

Max Activating Token Index: 8

Text #12

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0829. Min Act: -0.0001

Data Index: 1552544 (Python Code)

Max Activating Token Index: 13

Text #13

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0809. Min Act: -0.0001

Data Index: 1040595 (C4 (Web Text))

Max Activating Token Index: 5

Text #14

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0797. Min Act: -0.0001

Data Index: 800678 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0763. Min Act: -0.0001

Data Index: 1431146 (Python Code)

Max Activating Token Index: 15

Text #16

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0739. Min Act: -0.0001

Data Index: 297479 (C4 (Web Text))

Max Activating Token Index: 6

Text #17

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0767. Min Act: -0.0001

Data Index: 193357 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0769. Min Act: -0.0001

Data Index: 471029 (C4 (Web Text))

Max Activating Token Index: 107

Text #19

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0767. Min Act: -0.0001

Data Index: 1568207 (Python Code)

Max Activating Token Index: 11