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

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

Neuron 2463 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: 0.1122. Min Range: -0.1122

Max Act: 0.1111. Min Act: -0.0003

Data Index: 1202733 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.1122. Min Act: -0.0003

Data Index: 497131 (C4 (Web Text))

Max Activating Token Index: 510

Text #2

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.1118. Min Act: -0.0003

Data Index: 946255 (C4 (Web Text))

Max Activating Token Index: 529

Text #3

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.1106. Min Act: -0.0003

Data Index: 1352116 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.1074. Min Act: -0.0003

Data Index: 220276 (C4 (Web Text))

Max Activating Token Index: 509

Text #5

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.1059. Min Act: -0.0003

Data Index: 1207124 (C4 (Web Text))

Max Activating Token Index: 475

Text #6

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.1048. Min Act: -0.0003

Data Index: 172488 (C4 (Web Text))

Max Activating Token Index: 478

Text #7

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.1068. Min Act: -0.0003

Data Index: 806040 (C4 (Web Text))

Max Activating Token Index: 423

Text #8

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.1027. Min Act: -0.0003

Data Index: 1181283 (C4 (Web Text))

Max Activating Token Index: 439

Text #9

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.1024. Min Act: -0.0003

Data Index: 150908 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.1037. Min Act: -0.0003

Data Index: 440501 (C4 (Web Text))

Max Activating Token Index: 502

Text #11

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.1037. Min Act: -0.0003

Data Index: 614855 (C4 (Web Text))

Max Activating Token Index: 429

Text #12

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.1035. Min Act: -0.0003

Data Index: 1198876 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.1037. Min Act: -0.0003

Data Index: 773830 (C4 (Web Text))

Max Activating Token Index: 432

Text #14

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.1035. Min Act: -0.0003

Data Index: 1156051 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.1034. Min Act: -0.0003

Data Index: 865088 (C4 (Web Text))

Max Activating Token Index: 476

Text #16

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.1033. Min Act: -0.0003

Data Index: 106751 (C4 (Web Text))

Max Activating Token Index: 446

Text #17

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.1030. Min Act: -0.0003

Data Index: 834692 (C4 (Web Text))

Max Activating Token Index: 432

Text #18

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.1047. Min Act: -0.0003

Data Index: 886981 (C4 (Web Text))

Max Activating Token Index: 474

Text #19

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.1027. Min Act: -0.0003

Data Index: 94107 (C4 (Web Text))

Max Activating Token Index: 377