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

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

Neuron 3925 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0026. Min Act: -0.0001

Data Index: 426015 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0020. Min Act: -0.0001

Data Index: 1212015 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0018. Min Act: -0.0001

Data Index: 1529778 (Python Code)

Max Activating Token Index: 18

Text #3

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0018. Min Act: -0.0001

Data Index: 1446293 (Python Code)

Max Activating Token Index: 29

Text #4

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0018. Min Act: -0.0001

Data Index: 1648384 (Python Code)

Max Activating Token Index: 20

Text #5

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0018. Min Act: -0.0001

Data Index: 1431139 (Python Code)

Max Activating Token Index: 11

Text #6

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0017. Min Act: -0.0001

Data Index: 768738 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0017. Min Act: -0.0001

Data Index: 1587911 (Python Code)

Max Activating Token Index: 13

Text #8

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0017. Min Act: -0.0001

Data Index: 1456095 (Python Code)

Max Activating Token Index: 23

Text #9

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0017. Min Act: -0.0001

Data Index: 1572954 (Python Code)

Max Activating Token Index: 15

Text #10

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0018. Min Act: -0.0001

Data Index: 977707 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0016. Min Act: -0.0001

Data Index: 1368779 (Python Code)

Max Activating Token Index: 66

Text #12

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0015. Min Act: -0.0001

Data Index: 564033 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0015. Min Act: -0.0001

Data Index: 1531801 (Python Code)

Max Activating Token Index: 13

Text #14

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0015. Min Act: -0.0001

Data Index: 1476897 (Python Code)

Max Activating Token Index: 28

Text #15

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0015. Min Act: -0.0001

Data Index: 967727 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0015. Min Act: -0.0001

Data Index: 1411688 (Python Code)

Max Activating Token Index: 27

Text #17

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0015. Min Act: -0.0001

Data Index: 152271 (C4 (Web Text))

Max Activating Token Index: 5

Text #18

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0015. Min Act: -0.0001

Data Index: 1542263 (Python Code)

Max Activating Token Index: 19

Text #19

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0014. Min Act: -0.0001

Data Index: 1607267 (Python Code)

Max Activating Token Index: 25