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

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

Neuron 52 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.2708. Min Act: -0.0000

Data Index: 1365522 (Python Code)

Max Activating Token Index: 948

Text #1

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.2525. Min Act: -0.0000

Data Index: 1049446 (C4 (Web Text))

Max Activating Token Index: 733

Text #2

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.2173. Min Act: -0.0000

Data Index: 1593123 (Python Code)

Max Activating Token Index: 106

Text #3

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.2139. Min Act: -0.0000

Data Index: 1552232 (Python Code)

Max Activating Token Index: 748

Text #4

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.2180. Min Act: -0.0000

Data Index: 1559855 (Python Code)

Max Activating Token Index: 701

Text #5

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.2038. Min Act: -0.0000

Data Index: 1624420 (Python Code)

Max Activating Token Index: 405

Text #6

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.1893. Min Act: -0.0000

Data Index: 285262 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.1823. Min Act: -0.0000

Data Index: 1492736 (Python Code)

Max Activating Token Index: 902

Text #8

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.2046. Min Act: -0.0000

Data Index: 1396559 (Python Code)

Max Activating Token Index: 627

Text #9

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.1922. Min Act: -0.0000

Data Index: 592176 (C4 (Web Text))

Max Activating Token Index: 735

Text #10

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.1752. Min Act: -0.0000

Data Index: 451676 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.1895. Min Act: -0.0000

Data Index: 1613421 (Python Code)

Max Activating Token Index: 580

Text #12

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.1636. Min Act: -0.0000

Data Index: 1479568 (Python Code)

Max Activating Token Index: 903

Text #13

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.1912. Min Act: -0.0000

Data Index: 1453975 (Python Code)

Max Activating Token Index: 348

Text #14

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.1732. Min Act: -0.0000

Data Index: 387633 (C4 (Web Text))

Max Activating Token Index: 466

Text #15

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.1770. Min Act: -0.0000

Data Index: 933422 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.1766. Min Act: -0.0000

Data Index: 1635162 (Python Code)

Max Activating Token Index: 834

Text #17

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.2058. Min Act: -0.0000

Data Index: 1508906 (Python Code)

Max Activating Token Index: 878

Text #18

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.1691. Min Act: -0.0000

Data Index: 1401428 (Python Code)

Max Activating Token Index: 641

Text #19

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.1724. Min Act: -0.0000

Data Index: 205719 (C4 (Web Text))

Max Activating Token Index: 871