Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1015 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0068. Min Act: -0.0003

Data Index: 199877 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0065. Min Act: -0.0004

Data Index: 216362 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0063. Min Act: -0.0004

Data Index: 808407 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0061. Min Act: -0.0004

Data Index: 1085811 (C4 (Web Text))

Max Activating Token Index: 5

Text #4

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0061. Min Act: -0.0004

Data Index: 1232932 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0060. Min Act: -0.0003

Data Index: 915547 (C4 (Web Text))

Max Activating Token Index: 990

Text #6

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0060. Min Act: -0.0004

Data Index: 468108 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0060. Min Act: -0.0003

Data Index: 425125 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0060. Min Act: -0.0004

Data Index: 711317 (C4 (Web Text))

Max Activating Token Index: 553

Text #9

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0060. Min Act: -0.0003

Data Index: 939005 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0060. Min Act: -0.0004

Data Index: 1318735 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0058. Min Act: -0.0004

Data Index: 881535 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0058. Min Act: -0.0003

Data Index: 917418 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0057. Min Act: -0.0004

Data Index: 949219 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0058. Min Act: -0.0003

Data Index: 365545 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0056. Min Act: -0.0003

Data Index: 566115 (C4 (Web Text))

Max Activating Token Index: 816

Text #16

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0057. Min Act: -0.0004

Data Index: 1324253 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0057. Min Act: -0.0004

Data Index: 1359391 (C4 (Web Text))

Max Activating Token Index: 852

Text #18

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0055. Min Act: -0.0003

Data Index: 830914 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0057. Min Act: -0.0004

Data Index: 871586 (C4 (Web Text))

Max Activating Token Index: 81