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

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

Neuron 4802 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0040. Min Act: -0.0000

Data Index: 1607334 (Python Code)

Max Activating Token Index: 21

Text #1

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0036. Min Act: -0.0000

Data Index: 1645285 (Python Code)

Max Activating Token Index: 33

Text #2

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0026. Min Act: -0.0000

Data Index: 191195 (C4 (Web Text))

Max Activating Token Index: 258

Text #3

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0025. Min Act: -0.0000

Data Index: 1613461 (Python Code)

Max Activating Token Index: 35

Text #4

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0023. Min Act: -0.0000

Data Index: 1461144 (Python Code)

Max Activating Token Index: 616

Text #5

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0023. Min Act: -0.0000

Data Index: 1587465 (Python Code)

Max Activating Token Index: 46

Text #6

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0023. Min Act: -0.0000

Data Index: 1406960 (Python Code)

Max Activating Token Index: 28

Text #7

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0022. Min Act: -0.0000

Data Index: 1228524 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0022. Min Act: -0.0000

Data Index: 1562441 (Python Code)

Max Activating Token Index: 61

Text #9

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0018. Min Act: -0.0000

Data Index: 1516098 (Python Code)

Max Activating Token Index: 15

Text #10

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0021. Min Act: -0.0000

Data Index: 1499228 (Python Code)

Max Activating Token Index: 71

Text #11

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0020. Min Act: -0.0000

Data Index: 938370 (C4 (Web Text))

Max Activating Token Index: 235

Text #12

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0020. Min Act: -0.0000

Data Index: 1418573 (Python Code)

Max Activating Token Index: 24

Text #13

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0019. Min Act: -0.0000

Data Index: 1575305 (Python Code)

Max Activating Token Index: 41

Text #14

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0019. Min Act: -0.0000

Data Index: 176365 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0019. Min Act: -0.0000

Data Index: 1442306 (Python Code)

Max Activating Token Index: 20

Text #16

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0017. Min Act: -0.0000

Data Index: 1544298 (Python Code)

Max Activating Token Index: 24

Text #17

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0019. Min Act: -0.0000

Data Index: 1578802 (Python Code)

Max Activating Token Index: 34

Text #18

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0018. Min Act: -0.0000

Data Index: 1469357 (Python Code)

Max Activating Token Index: 12

Text #19

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0018. Min Act: -0.0000

Data Index: 1391003 (Python Code)

Max Activating Token Index: 12