Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 92 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0063. Min Act: -0.0004

Data Index: 130005 (C4 (Web Text))

Max Activating Token Index: 727

Text #1

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0059. Min Act: -0.0004

Data Index: 1595775 (Python Code)

Max Activating Token Index: 770

Text #2

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0057. Min Act: -0.0004

Data Index: 1260546 (C4 (Web Text))

Max Activating Token Index: 312

Text #3

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0057. Min Act: -0.0004

Data Index: 415061 (C4 (Web Text))

Max Activating Token Index: 525

Text #4

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0057. Min Act: -0.0004

Data Index: 229327 (C4 (Web Text))

Max Activating Token Index: 896

Text #5

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0057. Min Act: -0.0004

Data Index: 108140 (C4 (Web Text))

Max Activating Token Index: 675

Text #6

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0056. Min Act: -0.0004

Data Index: 1604841 (Python Code)

Max Activating Token Index: 141

Text #7

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0055. Min Act: -0.0004

Data Index: 1513017 (Python Code)

Max Activating Token Index: 1012

Text #8

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0055. Min Act: -0.0004

Data Index: 753421 (C4 (Web Text))

Max Activating Token Index: 202

Text #9

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0055. Min Act: -0.0004

Data Index: 158748 (C4 (Web Text))

Max Activating Token Index: 187

Text #10

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0054. Min Act: -0.0004

Data Index: 672856 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0054. Min Act: -0.0004

Data Index: 1164393 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0053. Min Act: -0.0004

Data Index: 1577695 (Python Code)

Max Activating Token Index: 703

Text #13

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0054. Min Act: -0.0004

Data Index: 645824 (C4 (Web Text))

Max Activating Token Index: 588

Text #14

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0054. Min Act: -0.0004

Data Index: 187837 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0053. Min Act: -0.0004

Data Index: 427319 (C4 (Web Text))

Max Activating Token Index: 463

Text #16

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0053. Min Act: -0.0004

Data Index: 1384775 (Python Code)

Max Activating Token Index: 778

Text #17

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0053. Min Act: -0.0004

Data Index: 886229 (C4 (Web Text))

Max Activating Token Index: 719

Text #18

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0053. Min Act: -0.0005

Data Index: 926241 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0053. Min Act: -0.0005

Data Index: 1351538 (C4 (Web Text))

Max Activating Token Index: 559