Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1264 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1399. Min Act: -0.0002

Data Index: 845875 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1178. Min Act: -0.0002

Data Index: 1283254 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1147. Min Act: -0.0002

Data Index: 774852 (C4 (Web Text))

Max Activating Token Index: 209

Text #3

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1054. Min Act: -0.0001

Data Index: 1176331 (C4 (Web Text))

Max Activating Token Index: 863

Text #4

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1094. Min Act: -0.0002

Data Index: 1124916 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1013. Min Act: -0.0002

Data Index: 418870 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1042. Min Act: -0.0002

Data Index: 653467 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1083. Min Act: -0.0002

Data Index: 161168 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1063. Min Act: -0.0002

Data Index: 201767 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1034. Min Act: -0.0002

Data Index: 462810 (C4 (Web Text))

Max Activating Token Index: 818

Text #10

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1080. Min Act: -0.0002

Data Index: 123059 (C4 (Web Text))

Max Activating Token Index: 286

Text #11

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1036. Min Act: -0.0002

Data Index: 1246477 (C4 (Web Text))

Max Activating Token Index: 80

Text #12

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1103. Min Act: -0.0002

Data Index: 839791 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1042. Min Act: -0.0002

Data Index: 1121796 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1072. Min Act: -0.0001

Data Index: 1075575 (C4 (Web Text))

Max Activating Token Index: 878

Text #15

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.0995. Min Act: -0.0002

Data Index: 724864 (C4 (Web Text))

Max Activating Token Index: 804

Text #16

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.0997. Min Act: -0.0002

Data Index: 742345 (C4 (Web Text))

Max Activating Token Index: 873

Text #17

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1018. Min Act: -0.0001

Data Index: 437660 (C4 (Web Text))

Max Activating Token Index: 927

Text #18

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1037. Min Act: -0.0002

Data Index: 384375 (C4 (Web Text))

Max Activating Token Index: 179

Text #19

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1014. Min Act: -0.0002

Data Index: 978009 (C4 (Web Text))

Max Activating Token Index: 824