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

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

Neuron 546 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1258. Min Act: -0.0002

Data Index: 1547442 (Python Code)

Max Activating Token Index: 610

Text #1

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1216. Min Act: -0.0002

Data Index: 1472159 (Python Code)

Max Activating Token Index: 209

Text #2

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1096. Min Act: -0.0002

Data Index: 1478984 (Python Code)

Max Activating Token Index: 250

Text #3

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1066. Min Act: -0.0002

Data Index: 1368593 (Python Code)

Max Activating Token Index: 954

Text #4

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1127. Min Act: -0.0002

Data Index: 1534445 (Python Code)

Max Activating Token Index: 561

Text #5

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1127. Min Act: -0.0002

Data Index: 1486113 (Python Code)

Max Activating Token Index: 844

Text #6

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1119. Min Act: -0.0002

Data Index: 1481505 (Python Code)

Max Activating Token Index: 228

Text #7

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1096. Min Act: -0.0002

Data Index: 1383898 (Python Code)

Max Activating Token Index: 584

Text #8

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1100. Min Act: -0.0002

Data Index: 1383729 (Python Code)

Max Activating Token Index: 635

Text #9

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1090. Min Act: -0.0002

Data Index: 1581944 (Python Code)

Max Activating Token Index: 152

Text #10

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0978. Min Act: -0.0002

Data Index: 1611142 (Python Code)

Max Activating Token Index: 815

Text #11

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1089. Min Act: -0.0002

Data Index: 1478885 (Python Code)

Max Activating Token Index: 816

Text #12

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1127. Min Act: -0.0002

Data Index: 1617229 (Python Code)

Max Activating Token Index: 759

Text #13

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1081. Min Act: -0.0002

Data Index: 1571017 (Python Code)

Max Activating Token Index: 613

Text #14

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1079. Min Act: -0.0002

Data Index: 1468607 (Python Code)

Max Activating Token Index: 123

Text #15

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1109. Min Act: -0.0002

Data Index: 1375573 (Python Code)

Max Activating Token Index: 109

Text #16

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1063. Min Act: -0.0002

Data Index: 1495433 (Python Code)

Max Activating Token Index: 148

Text #17

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1065. Min Act: -0.0002

Data Index: 1466552 (Python Code)

Max Activating Token Index: 400

Text #18

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1054. Min Act: -0.0002

Data Index: 1534528 (Python Code)

Max Activating Token Index: 840

Text #19

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1016. Min Act: -0.0002

Data Index: 1600926 (Python Code)

Max Activating Token Index: 207