Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 2012 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0090. Min Act: -0.0005

Data Index: 1609493 (Python Code)

Max Activating Token Index: 47

Text #1

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0087. Min Act: -0.0006

Data Index: 1550670 (Python Code)

Max Activating Token Index: 113

Text #2

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0086. Min Act: -0.0006

Data Index: 1428305 (Python Code)

Max Activating Token Index: 128

Text #3

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0083. Min Act: -0.0005

Data Index: 1521928 (Python Code)

Max Activating Token Index: 700

Text #4

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0081. Min Act: -0.0005

Data Index: 1435609 (Python Code)

Max Activating Token Index: 961

Text #5

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0080. Min Act: -0.0006

Data Index: 1520795 (Python Code)

Max Activating Token Index: 377

Text #6

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0078. Min Act: -0.0005

Data Index: 1518327 (Python Code)

Max Activating Token Index: 531

Text #7

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0079. Min Act: -0.0005

Data Index: 1108540 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0076. Min Act: -0.0006

Data Index: 1589303 (Python Code)

Max Activating Token Index: 699

Text #9

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0077. Min Act: -0.0006

Data Index: 957386 (C4 (Web Text))

Max Activating Token Index: 118

Text #10

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0075. Min Act: -0.0006

Data Index: 528773 (C4 (Web Text))

Max Activating Token Index: 148

Text #11

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0074. Min Act: -0.0005

Data Index: 463914 (C4 (Web Text))

Max Activating Token Index: 997

Text #12

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0074. Min Act: -0.0006

Data Index: 614496 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0073. Min Act: -0.0005

Data Index: 1228679 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0071. Min Act: -0.0005

Data Index: 808499 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0073. Min Act: -0.0006

Data Index: 1114774 (C4 (Web Text))

Max Activating Token Index: 961

Text #16

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0071. Min Act: -0.0005

Data Index: 1571479 (Python Code)

Max Activating Token Index: 5

Text #17

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0070. Min Act: -0.0006

Data Index: 1365621 (Python Code)

Max Activating Token Index: 585

Text #18

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0070. Min Act: -0.0006

Data Index: 737784 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0070. Min Act: -0.0005

Data Index: 103812 (C4 (Web Text))

Max Activating Token Index: 147