Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 300 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1210. Min Act: -0.0001

Data Index: 214709 (C4 (Web Text))

Max Activating Token Index: 1011

Text #1

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1200. Min Act: -0.0001

Data Index: 108973 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1187. Min Act: -0.0001

Data Index: 1146883 (C4 (Web Text))

Max Activating Token Index: 571

Text #3

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1176. Min Act: -0.0001

Data Index: 191133 (C4 (Web Text))

Max Activating Token Index: 1009

Text #4

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1018. Min Act: -0.0001

Data Index: 427619 (C4 (Web Text))

Max Activating Token Index: 922

Text #5

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1219. Min Act: -0.0001

Data Index: 852572 (C4 (Web Text))

Max Activating Token Index: 739

Text #6

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1074. Min Act: -0.0001

Data Index: 1296012 (C4 (Web Text))

Max Activating Token Index: 919

Text #7

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1058. Min Act: -0.0001

Data Index: 1280220 (C4 (Web Text))

Max Activating Token Index: 387

Text #8

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1104. Min Act: -0.0001

Data Index: 101525 (C4 (Web Text))

Max Activating Token Index: 461

Text #9

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1097. Min Act: -0.0001

Data Index: 907141 (C4 (Web Text))

Max Activating Token Index: 953

Text #10

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1082. Min Act: -0.0001

Data Index: 753900 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1111. Min Act: -0.0001

Data Index: 326897 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0979. Min Act: -0.0001

Data Index: 888950 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0979. Min Act: -0.0001

Data Index: 1088650 (C4 (Web Text))

Max Activating Token Index: 728

Text #14

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1056. Min Act: -0.0001

Data Index: 289488 (C4 (Web Text))

Max Activating Token Index: 308

Text #15

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1016. Min Act: -0.0001

Data Index: 242303 (C4 (Web Text))

Max Activating Token Index: 244

Text #16

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1064. Min Act: -0.0001

Data Index: 903808 (C4 (Web Text))

Max Activating Token Index: 896

Text #17

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1031. Min Act: -0.0001

Data Index: 112083 (C4 (Web Text))

Max Activating Token Index: 392

Text #18

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1082. Min Act: -0.0001

Data Index: 1113479 (C4 (Web Text))

Max Activating Token Index: 736

Text #19

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1002. Min Act: -0.0001

Data Index: 567008 (C4 (Web Text))

Max Activating Token Index: 733