Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2823 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1343. Min Act: -0.0002

Data Index: 386501 (C4 (Web Text))

Max Activating Token Index: 165

Text #1

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1226. Min Act: -0.0002

Data Index: 1157468 (C4 (Web Text))

Max Activating Token Index: 287

Text #2

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1096. Min Act: -0.0002

Data Index: 337622 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1086. Min Act: -0.0002

Data Index: 787599 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1076. Min Act: -0.0002

Data Index: 1153780 (C4 (Web Text))

Max Activating Token Index: 496

Text #5

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1054. Min Act: -0.0002

Data Index: 762235 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1101. Min Act: -0.0002

Data Index: 860976 (C4 (Web Text))

Max Activating Token Index: 416

Text #7

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1027. Min Act: -0.0002

Data Index: 171304 (C4 (Web Text))

Max Activating Token Index: 470

Text #8

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1082. Min Act: -0.0002

Data Index: 1073856 (C4 (Web Text))

Max Activating Token Index: 624

Text #9

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1065. Min Act: -0.0002

Data Index: 838970 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.0939. Min Act: -0.0002

Data Index: 959701 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.0988. Min Act: -0.0002

Data Index: 972890 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1047. Min Act: -0.0002

Data Index: 193475 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.0968. Min Act: -0.0002

Data Index: 657716 (C4 (Web Text))

Max Activating Token Index: 599

Text #14

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.0882. Min Act: -0.0002

Data Index: 786278 (C4 (Web Text))

Max Activating Token Index: 622

Text #15

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.0920. Min Act: -0.0002

Data Index: 685870 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.0951. Min Act: -0.0002

Data Index: 839744 (C4 (Web Text))

Max Activating Token Index: 964

Text #17

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.0856. Min Act: -0.0002

Data Index: 857173 (C4 (Web Text))

Max Activating Token Index: 924

Text #18

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.0894. Min Act: -0.0002

Data Index: 1255665 (C4 (Web Text))

Max Activating Token Index: 537

Text #19

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.0842. Min Act: -0.0002

Data Index: 449514 (C4 (Web Text))

Max Activating Token Index: 686