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

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

Neuron 5117 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0169. Min Act: -0.0000

Data Index: 306697 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0151. Min Act: -0.0000

Data Index: 1417336 (Python Code)

Max Activating Token Index: 123

Text #2

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0134. Min Act: -0.0000

Data Index: 1220388 (C4 (Web Text))

Max Activating Token Index: 110

Text #3

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0129. Min Act: -0.0000

Data Index: 811219 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0124. Min Act: -0.0000

Data Index: 129383 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0118. Min Act: -0.0000

Data Index: 798118 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0126. Min Act: -0.0000

Data Index: 716204 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0116. Min Act: -0.0000

Data Index: 87726 (C4 (Web Text))

Max Activating Token Index: 143

Text #8

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0122. Min Act: -0.0000

Data Index: 243180 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0115. Min Act: -0.0000

Data Index: 905800 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0112. Min Act: -0.0000

Data Index: 909812 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0115. Min Act: -0.0000

Data Index: 648143 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0119. Min Act: -0.0000

Data Index: 693127 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0113. Min Act: -0.0000

Data Index: 1597300 (Python Code)

Max Activating Token Index: 89

Text #14

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0111. Min Act: -0.0000

Data Index: 187563 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0111. Min Act: -0.0000

Data Index: 535698 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0115. Min Act: -0.0000

Data Index: 824582 (C4 (Web Text))

Max Activating Token Index: 72

Text #17

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0110. Min Act: -0.0000

Data Index: 1320254 (C4 (Web Text))

Max Activating Token Index: 70

Text #18

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0119. Min Act: -0.0000

Data Index: 1184329 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0115. Min Act: -0.0000

Data Index: 214612 (C4 (Web Text))

Max Activating Token Index: 34