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

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

Neuron 2229 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: 0.0016. Min Range: -0.0016

Max Act: 0.0016. Min Act: -0.0002

Data Index: 121919 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0015. Min Act: -0.0003

Data Index: 1372470 (Python Code)

Max Activating Token Index: 245

Text #2

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0015. Min Act: -0.0003

Data Index: 1535803 (Python Code)

Max Activating Token Index: 246

Text #3

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0015. Min Act: -0.0003

Data Index: 1481892 (Python Code)

Max Activating Token Index: 108

Text #4

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0014. Min Act: -0.0003

Data Index: 1653681 (Python Code)

Max Activating Token Index: 164

Text #5

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0014. Min Act: -0.0003

Data Index: 1621239 (Python Code)

Max Activating Token Index: 56

Text #6

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0014. Min Act: -0.0003

Data Index: 1480583 (Python Code)

Max Activating Token Index: 190

Text #7

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0014. Min Act: -0.0003

Data Index: 1639159 (Python Code)

Max Activating Token Index: 285

Text #8

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0014. Min Act: -0.0002

Data Index: 1003290 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0013. Min Act: -0.0003

Data Index: 1367651 (Python Code)

Max Activating Token Index: 73

Text #10

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0013. Min Act: -0.0004

Data Index: 1311173 (C4 (Web Text))

Max Activating Token Index: 205

Text #11

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0013. Min Act: -0.0004

Data Index: 613155 (C4 (Web Text))

Max Activating Token Index: 126

Text #12

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0013. Min Act: -0.0003

Data Index: 1649313 (Python Code)

Max Activating Token Index: 191

Text #13

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0013. Min Act: -0.0004

Data Index: 749062 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0013. Min Act: -0.0003

Data Index: 1568939 (Python Code)

Max Activating Token Index: 143

Text #15

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0013. Min Act: -0.0003

Data Index: 1039331 (C4 (Web Text))

Max Activating Token Index: 55

Text #16

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0012. Min Act: -0.0003

Data Index: 1644545 (Python Code)

Max Activating Token Index: 153

Text #17

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0012. Min Act: -0.0003

Data Index: 1417444 (Python Code)

Max Activating Token Index: 77

Text #18

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0012. Min Act: -0.0004

Data Index: 302189 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0012. Min Act: -0.0003

Data Index: 1081886 (C4 (Web Text))

Max Activating Token Index: 184