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

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

Neuron 5423 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: 1.3970. Min Range: -1.3970

Max Act: 1.3970. Min Act: -0.0000

Data Index: 1399589 (Python Code)

Max Activating Token Index: 5

Text #1

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.2776. Min Act: -0.0000

Data Index: 1587764 (Python Code)

Max Activating Token Index: 16

Text #2

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.3358. Min Act: -0.0000

Data Index: 1471975 (Python Code)

Max Activating Token Index: 19

Text #3

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.1745. Min Act: -0.0000

Data Index: 1500251 (Python Code)

Max Activating Token Index: 767

Text #4

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.1605. Min Act: -0.0000

Data Index: 1551524 (Python Code)

Max Activating Token Index: 114

Text #5

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.1637. Min Act: -0.0000

Data Index: 1553305 (Python Code)

Max Activating Token Index: 12

Text #6

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.1483. Min Act: -0.0000

Data Index: 1493100 (Python Code)

Max Activating Token Index: 16

Text #7

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.1391. Min Act: -0.0000

Data Index: 1636553 (Python Code)

Max Activating Token Index: 54

Text #8

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.1198. Min Act: -0.0000

Data Index: 1569950 (Python Code)

Max Activating Token Index: 63

Text #9

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.1139. Min Act: -0.0000

Data Index: 1454493 (Python Code)

Max Activating Token Index: 73

Text #10

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.0370. Min Act: -0.0000

Data Index: 1570009 (Python Code)

Max Activating Token Index: 894

Text #11

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.0303. Min Act: -0.0000

Data Index: 1603029 (Python Code)

Max Activating Token Index: 92

Text #12

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.0634. Min Act: -0.0000

Data Index: 1365067 (Python Code)

Max Activating Token Index: 33

Text #13

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.0202. Min Act: -0.0000

Data Index: 1636622 (Python Code)

Max Activating Token Index: 150

Text #14

Max Range: 1.3970. Min Range: -1.3970

Max Act: 0.9910. Min Act: -0.0000

Data Index: 1504951 (Python Code)

Max Activating Token Index: 9

Text #15

Max Range: 1.3970. Min Range: -1.3970

Max Act: 0.9846. Min Act: -0.0000

Data Index: 1365689 (Python Code)

Max Activating Token Index: 33

Text #16

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.0413. Min Act: -0.0000

Data Index: 1515925 (Python Code)

Max Activating Token Index: 87

Text #17

Max Range: 1.3970. Min Range: -1.3970

Max Act: 0.9422. Min Act: -0.0000

Data Index: 1438100 (Python Code)

Max Activating Token Index: 22

Text #18

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.0263. Min Act: -0.0000

Data Index: 1644806 (Python Code)

Max Activating Token Index: 26

Text #19

Max Range: 1.3970. Min Range: -1.3970

Max Act: 0.9609. Min Act: -0.0000

Data Index: 1391083 (Python Code)

Max Activating Token Index: 5