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

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

Neuron 1390 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: 0.1728. Min Range: -0.1728

Max Act: 0.1728. Min Act: -0.0002

Data Index: 577799 (C4 (Web Text))

Max Activating Token Index: 761

Text #1

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1295. Min Act: -0.0002

Data Index: 816571 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1204. Min Act: -0.0002

Data Index: 1355712 (C4 (Web Text))

Max Activating Token Index: 175

Text #3

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1171. Min Act: -0.0002

Data Index: 1142625 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1191. Min Act: -0.0002

Data Index: 235827 (C4 (Web Text))

Max Activating Token Index: 449

Text #5

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1077. Min Act: -0.0002

Data Index: 591013 (C4 (Web Text))

Max Activating Token Index: 749

Text #6

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1050. Min Act: -0.0002

Data Index: 645256 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1083. Min Act: -0.0002

Data Index: 485773 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1075. Min Act: -0.0002

Data Index: 523052 (C4 (Web Text))

Max Activating Token Index: 722

Text #9

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1093. Min Act: -0.0002

Data Index: 1339422 (C4 (Web Text))

Max Activating Token Index: 967

Text #10

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1087. Min Act: -0.0002

Data Index: 869976 (C4 (Web Text))

Max Activating Token Index: 1011

Text #11

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1103. Min Act: -0.0002

Data Index: 1122061 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1093. Min Act: -0.0002

Data Index: 548180 (C4 (Web Text))

Max Activating Token Index: 859

Text #13

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1060. Min Act: -0.0002

Data Index: 1321024 (C4 (Web Text))

Max Activating Token Index: 185

Text #14

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1047. Min Act: -0.0002

Data Index: 1404151 (Python Code)

Max Activating Token Index: 614

Text #15

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1037. Min Act: -0.0002

Data Index: 626635 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1035. Min Act: -0.0002

Data Index: 1165064 (C4 (Web Text))

Max Activating Token Index: 563

Text #17

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1036. Min Act: -0.0002

Data Index: 1367425 (Python Code)

Max Activating Token Index: 258

Text #18

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.0974. Min Act: -0.0002

Data Index: 166260 (C4 (Web Text))

Max Activating Token Index: 757

Text #19

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.0958. Min Act: -0.0002

Data Index: 80102 (C4 (Web Text))

Max Activating Token Index: 220