Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1714 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1219. Min Act: -0.0004

Data Index: 1431965 (Python Code)

Max Activating Token Index: 735

Text #1

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1231. Min Act: -0.0003

Data Index: 1487068 (Python Code)

Max Activating Token Index: 252

Text #2

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1119. Min Act: -0.0003

Data Index: 1588154 (Python Code)

Max Activating Token Index: 94

Text #3

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1184. Min Act: -0.0003

Data Index: 1583813 (Python Code)

Max Activating Token Index: 241

Text #4

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1071. Min Act: -0.0003

Data Index: 1363855 (Python Code)

Max Activating Token Index: 303

Text #5

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1114. Min Act: -0.0003

Data Index: 1594990 (Python Code)

Max Activating Token Index: 262

Text #6

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1072. Min Act: -0.0003

Data Index: 1479876 (Python Code)

Max Activating Token Index: 109

Text #7

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1078. Min Act: -0.0003

Data Index: 1607017 (Python Code)

Max Activating Token Index: 147

Text #8

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1083. Min Act: -0.0003

Data Index: 1361841 (Python Code)

Max Activating Token Index: 349

Text #9

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1062. Min Act: -0.0003

Data Index: 1481530 (Python Code)

Max Activating Token Index: 445

Text #10

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1060. Min Act: -0.0003

Data Index: 1366521 (Python Code)

Max Activating Token Index: 207

Text #11

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1082. Min Act: -0.0003

Data Index: 1370222 (Python Code)

Max Activating Token Index: 890

Text #12

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1086. Min Act: -0.0003

Data Index: 1574459 (Python Code)

Max Activating Token Index: 576

Text #13

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1025. Min Act: -0.0003

Data Index: 1602370 (Python Code)

Max Activating Token Index: 618

Text #14

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1024. Min Act: -0.0003

Data Index: 1369285 (Python Code)

Max Activating Token Index: 729

Text #15

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1041. Min Act: -0.0003

Data Index: 1381515 (Python Code)

Max Activating Token Index: 5

Text #16

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1016. Min Act: -0.0003

Data Index: 1506919 (Python Code)

Max Activating Token Index: 746

Text #17

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1042. Min Act: -0.0002

Data Index: 1484616 (Python Code)

Max Activating Token Index: 553

Text #18

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1050. Min Act: -0.0003

Data Index: 1465687 (Python Code)

Max Activating Token Index: 699

Text #19

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0965. Min Act: -0.0004

Data Index: 1638699 (Python Code)

Max Activating Token Index: 406