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

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

Neuron 4246 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: 0.1245. Min Range: -0.1245

Max Act: 0.1242. Min Act: -0.0002

Data Index: 1536258 (Python Code)

Max Activating Token Index: 13

Text #1

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1098. Min Act: -0.0002

Data Index: 1405825 (Python Code)

Max Activating Token Index: 235

Text #2

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1133. Min Act: -0.0002

Data Index: 1564207 (Python Code)

Max Activating Token Index: 73

Text #3

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1183. Min Act: -0.0002

Data Index: 1464567 (Python Code)

Max Activating Token Index: 553

Text #4

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1200. Min Act: -0.0002

Data Index: 1468602 (Python Code)

Max Activating Token Index: 454

Text #5

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1190. Min Act: -0.0002

Data Index: 1569595 (Python Code)

Max Activating Token Index: 724

Text #6

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1245. Min Act: -0.0002

Data Index: 1487831 (Python Code)

Max Activating Token Index: 767

Text #7

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1153. Min Act: -0.0002

Data Index: 1590533 (Python Code)

Max Activating Token Index: 33

Text #8

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1229. Min Act: -0.0002

Data Index: 1635648 (Python Code)

Max Activating Token Index: 338

Text #9

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1072. Min Act: -0.0002

Data Index: 1546946 (Python Code)

Max Activating Token Index: 107

Text #10

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1192. Min Act: -0.0002

Data Index: 1541096 (Python Code)

Max Activating Token Index: 31

Text #11

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1145. Min Act: -0.0002

Data Index: 1410338 (Python Code)

Max Activating Token Index: 119

Text #12

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1087. Min Act: -0.0002

Data Index: 1391157 (Python Code)

Max Activating Token Index: 58

Text #13

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1180. Min Act: -0.0002

Data Index: 1652270 (Python Code)

Max Activating Token Index: 26

Text #14

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1195. Min Act: -0.0002

Data Index: 1477885 (Python Code)

Max Activating Token Index: 904

Text #15

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1151. Min Act: -0.0002

Data Index: 1505391 (Python Code)

Max Activating Token Index: 66

Text #16

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1115. Min Act: -0.0002

Data Index: 1597341 (Python Code)

Max Activating Token Index: 18

Text #17

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0996. Min Act: -0.0002

Data Index: 1390225 (Python Code)

Max Activating Token Index: 616

Text #18

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1064. Min Act: -0.0002

Data Index: 1554257 (Python Code)

Max Activating Token Index: 272

Text #19

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1141. Min Act: -0.0002

Data Index: 1644900 (Python Code)

Max Activating Token Index: 76