Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3820 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1501. Min Act: -0.0002

Data Index: 197851 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1453. Min Act: -0.0002

Data Index: 474308 (C4 (Web Text))

Max Activating Token Index: 495

Text #2

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1193. Min Act: -0.0002

Data Index: 109241 (C4 (Web Text))

Max Activating Token Index: 674

Text #3

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1072. Min Act: -0.0002

Data Index: 546683 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1098. Min Act: -0.0002

Data Index: 633691 (C4 (Web Text))

Max Activating Token Index: 354

Text #5

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1138. Min Act: -0.0002

Data Index: 986248 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1082. Min Act: -0.0002

Data Index: 942116 (C4 (Web Text))

Max Activating Token Index: 329

Text #7

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1124. Min Act: -0.0002

Data Index: 90847 (C4 (Web Text))

Max Activating Token Index: 363

Text #8

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1072. Min Act: -0.0002

Data Index: 404404 (C4 (Web Text))

Max Activating Token Index: 587

Text #9

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1074. Min Act: -0.0002

Data Index: 733726 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1095. Min Act: -0.0002

Data Index: 1367805 (Python Code)

Max Activating Token Index: 236

Text #11

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1058. Min Act: -0.0002

Data Index: 665961 (C4 (Web Text))

Max Activating Token Index: 481

Text #12

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1039. Min Act: -0.0002

Data Index: 1108013 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1037. Min Act: -0.0002

Data Index: 723103 (C4 (Web Text))

Max Activating Token Index: 463

Text #14

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1002. Min Act: -0.0002

Data Index: 601408 (C4 (Web Text))

Max Activating Token Index: 714

Text #15

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.0999. Min Act: -0.0002

Data Index: 1473402 (Python Code)

Max Activating Token Index: 213

Text #16

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.0997. Min Act: -0.0002

Data Index: 203723 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.0980. Min Act: -0.0002

Data Index: 334422 (C4 (Web Text))

Max Activating Token Index: 151

Text #18

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1004. Min Act: -0.0002

Data Index: 1581095 (Python Code)

Max Activating Token Index: 1007

Text #19

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.0965. Min Act: -0.0002

Data Index: 1012562 (C4 (Web Text))

Max Activating Token Index: 597