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

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

Neuron 251 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0081. Min Act: -0.0001

Data Index: 1094677 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0076. Min Act: -0.0001

Data Index: 1139985 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0074. Min Act: -0.0001

Data Index: 1332614 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0068. Min Act: -0.0001

Data Index: 1044398 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0066. Min Act: -0.0001

Data Index: 1359966 (Python Code)

Max Activating Token Index: 105

Text #5

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0066. Min Act: -0.0001

Data Index: 1305676 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0068. Min Act: -0.0000

Data Index: 1520011 (Python Code)

Max Activating Token Index: 114

Text #7

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0067. Min Act: -0.0001

Data Index: 1587537 (Python Code)

Max Activating Token Index: 67

Text #8

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0068. Min Act: -0.0001

Data Index: 788764 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0067. Min Act: -0.0001

Data Index: 1029627 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0066. Min Act: -0.0000

Data Index: 1509758 (Python Code)

Max Activating Token Index: 63

Text #11

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0066. Min Act: -0.0001

Data Index: 181178 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0068. Min Act: -0.0001

Data Index: 1011708 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0065. Min Act: -0.0001

Data Index: 1198738 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0063. Min Act: -0.0001

Data Index: 123743 (C4 (Web Text))

Max Activating Token Index: 155

Text #15

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0067. Min Act: -0.0001

Data Index: 1064660 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0063. Min Act: -0.0001

Data Index: 1183712 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0064. Min Act: -0.0000

Data Index: 1506835 (Python Code)

Max Activating Token Index: 28

Text #18

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0065. Min Act: -0.0001

Data Index: 1184756 (C4 (Web Text))

Max Activating Token Index: 81

Text #19

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0062. Min Act: -0.0001

Data Index: 1022136 (C4 (Web Text))

Max Activating Token Index: 45