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

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

Neuron 2103 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1227. Min Act: -0.0003

Data Index: 938699 (C4 (Web Text))

Max Activating Token Index: 672

Text #1

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1111. Min Act: -0.0003

Data Index: 1303620 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1129. Min Act: -0.0003

Data Index: 806276 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1048. Min Act: -0.0003

Data Index: 234215 (C4 (Web Text))

Max Activating Token Index: 594

Text #4

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1034. Min Act: -0.0003

Data Index: 765505 (C4 (Web Text))

Max Activating Token Index: 526

Text #5

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1031. Min Act: -0.0003

Data Index: 456206 (C4 (Web Text))

Max Activating Token Index: 694

Text #6

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.0972. Min Act: -0.0003

Data Index: 597935 (C4 (Web Text))

Max Activating Token Index: 886

Text #7

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1081. Min Act: -0.0003

Data Index: 768350 (C4 (Web Text))

Max Activating Token Index: 673

Text #8

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1003. Min Act: -0.0003

Data Index: 922128 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.0988. Min Act: -0.0003

Data Index: 110370 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1022. Min Act: -0.0003

Data Index: 1016443 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1027. Min Act: -0.0003

Data Index: 1105942 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.0986. Min Act: -0.0003

Data Index: 190030 (C4 (Web Text))

Max Activating Token Index: 961

Text #13

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1014. Min Act: -0.0003

Data Index: 1008275 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1083. Min Act: -0.0003

Data Index: 447868 (C4 (Web Text))

Max Activating Token Index: 720

Text #15

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1007. Min Act: -0.0003

Data Index: 338530 (C4 (Web Text))

Max Activating Token Index: 743

Text #16

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1002. Min Act: -0.0003

Data Index: 223066 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.0946. Min Act: -0.0003

Data Index: 1285445 (C4 (Web Text))

Max Activating Token Index: 849

Text #18

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.0998. Min Act: -0.0003

Data Index: 1014949 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.0993. Min Act: -0.0003

Data Index: 480033 (C4 (Web Text))

Max Activating Token Index: 184