Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3460 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1258. Min Act: -0.0004

Data Index: 124336 (C4 (Web Text))

Max Activating Token Index: 856

Text #1

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1064. Min Act: -0.0003

Data Index: 546970 (C4 (Web Text))

Max Activating Token Index: 115

Text #2

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1235. Min Act: -0.0003

Data Index: 9900 (C4 (Web Text))

Max Activating Token Index: 563

Text #3

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1093. Min Act: -0.0003

Data Index: 955892 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1034. Min Act: -0.0003

Data Index: 224072 (C4 (Web Text))

Max Activating Token Index: 303

Text #5

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1102. Min Act: -0.0003

Data Index: 184233 (C4 (Web Text))

Max Activating Token Index: 17

Text #6

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1016. Min Act: -0.0003

Data Index: 662052 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0879. Min Act: -0.0003

Data Index: 1251541 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0977. Min Act: -0.0003

Data Index: 1016107 (C4 (Web Text))

Max Activating Token Index: 580

Text #9

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1092. Min Act: -0.0003

Data Index: 572302 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1004. Min Act: -0.0004

Data Index: 312465 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0959. Min Act: -0.0003

Data Index: 564274 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0996. Min Act: -0.0003

Data Index: 479964 (C4 (Web Text))

Max Activating Token Index: 115

Text #13

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0991. Min Act: -0.0003

Data Index: 179322 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0985. Min Act: -0.0003

Data Index: 996330 (C4 (Web Text))

Max Activating Token Index: 388

Text #15

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0911. Min Act: -0.0004

Data Index: 343114 (C4 (Web Text))

Max Activating Token Index: 259

Text #16

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1014. Min Act: -0.0003

Data Index: 684227 (C4 (Web Text))

Max Activating Token Index: 612

Text #17

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0966. Min Act: -0.0004

Data Index: 342526 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1030. Min Act: -0.0003

Data Index: 930335 (C4 (Web Text))

Max Activating Token Index: 703

Text #19

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1023. Min Act: -0.0003

Data Index: 506450 (C4 (Web Text))

Max Activating Token Index: 245