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

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

Neuron 1232 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0105. Min Act: -0.0003

Data Index: 458520 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0085. Min Act: -0.0003

Data Index: 69879 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0091. Min Act: -0.0002

Data Index: 1491642 (Python Code)

Max Activating Token Index: 146

Text #3

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0084. Min Act: -0.0002

Data Index: 1552460 (Python Code)

Max Activating Token Index: 259

Text #4

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0083. Min Act: -0.0002

Data Index: 1376112 (Python Code)

Max Activating Token Index: 261

Text #5

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0079. Min Act: -0.0003

Data Index: 280821 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0074. Min Act: -0.0003

Data Index: 1608737 (Python Code)

Max Activating Token Index: 122

Text #7

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0079. Min Act: -0.0003

Data Index: 813383 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0073. Min Act: -0.0003

Data Index: 1433749 (Python Code)

Max Activating Token Index: 69

Text #9

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0077. Min Act: -0.0003

Data Index: 1601488 (Python Code)

Max Activating Token Index: 301

Text #10

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0075. Min Act: -0.0003

Data Index: 1621560 (Python Code)

Max Activating Token Index: 187

Text #11

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0075. Min Act: -0.0003

Data Index: 1432727 (Python Code)

Max Activating Token Index: 48

Text #12

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0078. Min Act: -0.0002

Data Index: 1487048 (Python Code)

Max Activating Token Index: 83

Text #13

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0073. Min Act: -0.0003

Data Index: 1563570 (Python Code)

Max Activating Token Index: 154

Text #14

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0072. Min Act: -0.0002

Data Index: 1438424 (Python Code)

Max Activating Token Index: 128

Text #15

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0069. Min Act: -0.0002

Data Index: 1386621 (Python Code)

Max Activating Token Index: 59

Text #16

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0071. Min Act: -0.0002

Data Index: 1423450 (Python Code)

Max Activating Token Index: 86

Text #17

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0075. Min Act: -0.0002

Data Index: 55110 (C4 (Web Text))

Max Activating Token Index: 100

Text #18

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0071. Min Act: -0.0003

Data Index: 1472477 (Python Code)

Max Activating Token Index: 210

Text #19

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0076. Min Act: -0.0003

Data Index: 1433400 (Python Code)

Max Activating Token Index: 366