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

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

Neuron 245 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: 0.1185. Min Range: -0.1185

Max Act: 0.1185. Min Act: -0.0003

Data Index: 148637 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.1166. Min Act: -0.0003

Data Index: 559883 (C4 (Web Text))

Max Activating Token Index: 589

Text #2

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.1072. Min Act: -0.0003

Data Index: 476450 (C4 (Web Text))

Max Activating Token Index: 362

Text #3

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.1049. Min Act: -0.0003

Data Index: 143943 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.1068. Min Act: -0.0003

Data Index: 542041 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.1039. Min Act: -0.0003

Data Index: 1004995 (C4 (Web Text))

Max Activating Token Index: 405

Text #6

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.1022. Min Act: -0.0003

Data Index: 158018 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.1083. Min Act: -0.0003

Data Index: 986498 (C4 (Web Text))

Max Activating Token Index: 537

Text #8

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0965. Min Act: -0.0003

Data Index: 825963 (C4 (Web Text))

Max Activating Token Index: 643

Text #9

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0797. Min Act: -0.0003

Data Index: 336758 (C4 (Web Text))

Max Activating Token Index: 619

Text #10

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0997. Min Act: -0.0003

Data Index: 158282 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0992. Min Act: -0.0003

Data Index: 985443 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.1015. Min Act: -0.0003

Data Index: 7848 (C4 (Web Text))

Max Activating Token Index: 151

Text #13

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0987. Min Act: -0.0003

Data Index: 589282 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0998. Min Act: -0.0003

Data Index: 449863 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0863. Min Act: -0.0003

Data Index: 752234 (C4 (Web Text))

Max Activating Token Index: 266

Text #16

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0918. Min Act: -0.0003

Data Index: 152097 (C4 (Web Text))

Max Activating Token Index: 451

Text #17

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0886. Min Act: -0.0003

Data Index: 795080 (C4 (Web Text))

Max Activating Token Index: 37

Text #18

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0911. Min Act: -0.0003

Data Index: 716223 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0969. Min Act: -0.0003

Data Index: 172322 (C4 (Web Text))

Max Activating Token Index: 602