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

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

Neuron 3329 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0083. Min Act: -0.0002

Data Index: 1482249 (Python Code)

Max Activating Token Index: 842

Text #1

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0081. Min Act: -0.0002

Data Index: 1574694 (Python Code)

Max Activating Token Index: 153

Text #2

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0080. Min Act: -0.0002

Data Index: 1600161 (Python Code)

Max Activating Token Index: 159

Text #3

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0080. Min Act: -0.0002

Data Index: 1420807 (Python Code)

Max Activating Token Index: 106

Text #4

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0079. Min Act: -0.0002

Data Index: 1556151 (Python Code)

Max Activating Token Index: 19

Text #5

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0078. Min Act: -0.0002

Data Index: 1445885 (Python Code)

Max Activating Token Index: 178

Text #6

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0079. Min Act: -0.0002

Data Index: 1418781 (Python Code)

Max Activating Token Index: 93

Text #7

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0079. Min Act: -0.0002

Data Index: 1540405 (Python Code)

Max Activating Token Index: 316

Text #8

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0079. Min Act: -0.0002

Data Index: 1408299 (Python Code)

Max Activating Token Index: 17

Text #9

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0078. Min Act: -0.0002

Data Index: 1589882 (Python Code)

Max Activating Token Index: 202

Text #10

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0078. Min Act: -0.0002

Data Index: 1648594 (Python Code)

Max Activating Token Index: 469

Text #11

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0078. Min Act: -0.0002

Data Index: 1376815 (Python Code)

Max Activating Token Index: 336

Text #12

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0078. Min Act: -0.0002

Data Index: 1477754 (Python Code)

Max Activating Token Index: 24

Text #13

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0076. Min Act: -0.0002

Data Index: 1364373 (Python Code)

Max Activating Token Index: 123

Text #14

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0075. Min Act: -0.0002

Data Index: 1529928 (Python Code)

Max Activating Token Index: 738

Text #15

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0076. Min Act: -0.0002

Data Index: 1398959 (Python Code)

Max Activating Token Index: 160

Text #16

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0076. Min Act: -0.0002

Data Index: 1432522 (Python Code)

Max Activating Token Index: 245

Text #17

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0076. Min Act: -0.0002

Data Index: 1500060 (Python Code)

Max Activating Token Index: 343

Text #18

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0076. Min Act: -0.0002

Data Index: 1431662 (Python Code)

Max Activating Token Index: 410

Text #19

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0076. Min Act: -0.0002

Data Index: 1490832 (Python Code)

Max Activating Token Index: 23