Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 2005 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0093. Min Act: -0.0004

Data Index: 59383 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0090. Min Act: -0.0004

Data Index: 1577207 (Python Code)

Max Activating Token Index: 26

Text #2

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0083. Min Act: -0.0005

Data Index: 848975 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0076. Min Act: -0.0004

Data Index: 1521267 (Python Code)

Max Activating Token Index: 76

Text #4

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0076. Min Act: -0.0005

Data Index: 435591 (C4 (Web Text))

Max Activating Token Index: 120

Text #5

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0076. Min Act: -0.0004

Data Index: 1003042 (C4 (Web Text))

Max Activating Token Index: 73

Text #6

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0074. Min Act: -0.0004

Data Index: 407189 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0074. Min Act: -0.0004

Data Index: 825030 (C4 (Web Text))

Max Activating Token Index: 81

Text #8

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0074. Min Act: -0.0005

Data Index: 1299679 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0074. Min Act: -0.0005

Data Index: 863510 (C4 (Web Text))

Max Activating Token Index: 76

Text #10

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0075. Min Act: -0.0005

Data Index: 274207 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0073. Min Act: -0.0005

Data Index: 1515564 (Python Code)

Max Activating Token Index: 46

Text #12

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0073. Min Act: -0.0003

Data Index: 1193296 (C4 (Web Text))

Max Activating Token Index: 140

Text #13

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0074. Min Act: -0.0005

Data Index: 1238154 (C4 (Web Text))

Max Activating Token Index: 50

Text #14

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0073. Min Act: -0.0005

Data Index: 639491 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0074. Min Act: -0.0005

Data Index: 1132600 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0073. Min Act: -0.0005

Data Index: 1111653 (C4 (Web Text))

Max Activating Token Index: 79

Text #17

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0072. Min Act: -0.0005

Data Index: 1114537 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0074. Min Act: -0.0005

Data Index: 878555 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0072. Min Act: -0.0004

Data Index: 679350 (C4 (Web Text))

Max Activating Token Index: 105