Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0017. Min Act: -0.0003

Data Index: 1545615 (Python Code)

Max Activating Token Index: 84

Text #1

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0017. Min Act: -0.0003

Data Index: 1412927 (Python Code)

Max Activating Token Index: 21

Text #2

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0015. Min Act: -0.0003

Data Index: 1609545 (Python Code)

Max Activating Token Index: 33

Text #3

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0015. Min Act: -0.0003

Data Index: 1495090 (Python Code)

Max Activating Token Index: 820

Text #4

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0014. Min Act: -0.0003

Data Index: 1374714 (Python Code)

Max Activating Token Index: 63

Text #5

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0014. Min Act: -0.0003

Data Index: 1563905 (Python Code)

Max Activating Token Index: 33

Text #6

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0014. Min Act: -0.0003

Data Index: 1403148 (Python Code)

Max Activating Token Index: 80

Text #7

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0014. Min Act: -0.0003

Data Index: 1527505 (Python Code)

Max Activating Token Index: 47

Text #8

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0014. Min Act: -0.0003

Data Index: 1376359 (Python Code)

Max Activating Token Index: 79

Text #9

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0014. Min Act: -0.0003

Data Index: 1436815 (Python Code)

Max Activating Token Index: 167

Text #10

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0014. Min Act: -0.0003

Data Index: 1497359 (Python Code)

Max Activating Token Index: 48

Text #11

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0014. Min Act: -0.0003

Data Index: 1446486 (Python Code)

Max Activating Token Index: 45

Text #12

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0013. Min Act: -0.0003

Data Index: 1579267 (Python Code)

Max Activating Token Index: 987

Text #13

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0013. Min Act: -0.0003

Data Index: 1492010 (Python Code)

Max Activating Token Index: 600

Text #14

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0013. Min Act: -0.0003

Data Index: 1612356 (Python Code)

Max Activating Token Index: 600

Text #15

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0013. Min Act: -0.0003

Data Index: 1566587 (Python Code)

Max Activating Token Index: 23

Text #16

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0013. Min Act: -0.0003

Data Index: 1479673 (Python Code)

Max Activating Token Index: 75

Text #17

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0013. Min Act: -0.0003

Data Index: 1393875 (Python Code)

Max Activating Token Index: 133

Text #18

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0012. Min Act: -0.0003

Data Index: 1551901 (Python Code)

Max Activating Token Index: 310

Text #19

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0013. Min Act: -0.0003

Data Index: 1598279 (Python Code)

Max Activating Token Index: 202