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

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

Neuron 1049 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.1066. Min Act: -0.0000

Data Index: 1631300 (Python Code)

Max Activating Token Index: 13

Text #1

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0823. Min Act: -0.0000

Data Index: 1563704 (Python Code)

Max Activating Token Index: 14

Text #2

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0744. Min Act: -0.0000

Data Index: 1413906 (Python Code)

Max Activating Token Index: 15

Text #3

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0724. Min Act: -0.0000

Data Index: 921267 (C4 (Web Text))

Max Activating Token Index: 531

Text #4

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0725. Min Act: -0.0000

Data Index: 1366732 (Python Code)

Max Activating Token Index: 13

Text #5

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0725. Min Act: -0.0000

Data Index: 1387797 (Python Code)

Max Activating Token Index: 13

Text #6

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0725. Min Act: -0.0000

Data Index: 1405413 (Python Code)

Max Activating Token Index: 13

Text #7

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0725. Min Act: -0.0000

Data Index: 1366864 (Python Code)

Max Activating Token Index: 13

Text #8

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0725. Min Act: -0.0000

Data Index: 1463762 (Python Code)

Max Activating Token Index: 13

Text #9

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0725. Min Act: -0.0000

Data Index: 1577710 (Python Code)

Max Activating Token Index: 13

Text #10

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0725. Min Act: -0.0000

Data Index: 1414626 (Python Code)

Max Activating Token Index: 13

Text #11

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0725. Min Act: -0.0000

Data Index: 1444276 (Python Code)

Max Activating Token Index: 13

Text #12

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0725. Min Act: -0.0000

Data Index: 1586512 (Python Code)

Max Activating Token Index: 13

Text #13

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0693. Min Act: -0.0000

Data Index: 1451505 (Python Code)

Max Activating Token Index: 13

Text #14

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0663. Min Act: -0.0000

Data Index: 1486990 (Python Code)

Max Activating Token Index: 14

Text #15

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0666. Min Act: -0.0000

Data Index: 1640541 (Python Code)

Max Activating Token Index: 18

Text #16

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0666. Min Act: -0.0000

Data Index: 1526852 (Python Code)

Max Activating Token Index: 18

Text #17

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0649. Min Act: -0.0000

Data Index: 743896 (C4 (Web Text))

Max Activating Token Index: 246

Text #18

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0608. Min Act: -0.0000

Data Index: 1368067 (Python Code)

Max Activating Token Index: 10

Text #19

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0608. Min Act: -0.0000

Data Index: 1383378 (Python Code)

Max Activating Token Index: 10