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

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

Neuron 1397 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: 0.0072. Min Range: -0.0072

Max Act: 0.0072. Min Act: -0.0006

Data Index: 842441 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0061. Min Act: -0.0006

Data Index: 605942 (C4 (Web Text))

Max Activating Token Index: 332

Text #2

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0060. Min Act: -0.0006

Data Index: 1166974 (C4 (Web Text))

Max Activating Token Index: 134

Text #3

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0056. Min Act: -0.0006

Data Index: 571218 (C4 (Web Text))

Max Activating Token Index: 519

Text #4

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0057. Min Act: -0.0006

Data Index: 1280572 (C4 (Web Text))

Max Activating Token Index: 268

Text #5

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0055. Min Act: -0.0006

Data Index: 1126358 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0057. Min Act: -0.0006

Data Index: 834349 (C4 (Web Text))

Max Activating Token Index: 654

Text #7

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0057. Min Act: -0.0006

Data Index: 830153 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0055. Min Act: -0.0006

Data Index: 965673 (C4 (Web Text))

Max Activating Token Index: 83

Text #9

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0054. Min Act: -0.0006

Data Index: 156590 (C4 (Web Text))

Max Activating Token Index: 332

Text #10

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0053. Min Act: -0.0006

Data Index: 407713 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0053. Min Act: -0.0006

Data Index: 595747 (C4 (Web Text))

Max Activating Token Index: 672

Text #12

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0052. Min Act: -0.0006

Data Index: 1442089 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0051. Min Act: -0.0005

Data Index: 1474336 (Python Code)

Max Activating Token Index: 710

Text #14

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0051. Min Act: -0.0006

Data Index: 1095281 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0051. Min Act: -0.0006

Data Index: 1455728 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0051. Min Act: -0.0006

Data Index: 512627 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0051. Min Act: -0.0006

Data Index: 556129 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0049. Min Act: -0.0006

Data Index: 1091492 (C4 (Web Text))

Max Activating Token Index: 690

Text #19

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0050. Min Act: -0.0006

Data Index: 518285 (C4 (Web Text))

Max Activating Token Index: 634