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

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

Neuron 1371 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5086. Min Range: -1.5086

Max Act: 1.3083. Min Act: 0.0000

Data Index: 1527717 (Python Code)

Max Activating Token Index: 811

Text #1

Max Range: 1.5086. Min Range: -1.5086

Max Act: 1.5086. Min Act: -0.0000

Data Index: 1370349 (Python Code)

Max Activating Token Index: 673

Text #2

Max Range: 1.5086. Min Range: -1.5086

Max Act: 1.3896. Min Act: -0.0000

Data Index: 1026535 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 1.5086. Min Range: -1.5086

Max Act: 1.2877. Min Act: -0.0000

Data Index: 322524 (C4 (Web Text))

Max Activating Token Index: 133

Text #4

Max Range: 1.5086. Min Range: -1.5086

Max Act: 1.3774. Min Act: -0.0000

Data Index: 1443244 (Python Code)

Max Activating Token Index: 997

Text #5

Max Range: 1.5086. Min Range: -1.5086

Max Act: 1.1341. Min Act: -0.0000

Data Index: 1431717 (Python Code)

Max Activating Token Index: 722

Text #6

Max Range: 1.5086. Min Range: -1.5086

Max Act: 1.1887. Min Act: -0.0000

Data Index: 1175124 (C4 (Web Text))

Max Activating Token Index: 274

Text #7

Max Range: 1.5086. Min Range: -1.5086

Max Act: 1.0732. Min Act: -0.0000

Data Index: 1256125 (C4 (Web Text))

Max Activating Token Index: 660

Text #8

Max Range: 1.5086. Min Range: -1.5086

Max Act: 1.2427. Min Act: -0.0000

Data Index: 1471859 (Python Code)

Max Activating Token Index: 756

Text #9

Max Range: 1.5086. Min Range: -1.5086

Max Act: 1.1828. Min Act: -0.0000

Data Index: 844044 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 1.5086. Min Range: -1.5086

Max Act: 1.1994. Min Act: -0.0000

Data Index: 1596000 (Python Code)

Max Activating Token Index: 657

Text #11

Max Range: 1.5086. Min Range: -1.5086

Max Act: 1.1383. Min Act: -0.0000

Data Index: 1526108 (Python Code)

Max Activating Token Index: 595

Text #12

Max Range: 1.5086. Min Range: -1.5086

Max Act: 1.1050. Min Act: -0.0000

Data Index: 81267 (C4 (Web Text))

Max Activating Token Index: 882

Text #13

Max Range: 1.5086. Min Range: -1.5086

Max Act: 1.0772. Min Act: -0.0000

Data Index: 1507119 (Python Code)

Max Activating Token Index: 987

Text #14

Max Range: 1.5086. Min Range: -1.5086

Max Act: 1.0154. Min Act: -0.0000

Data Index: 414596 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 1.5086. Min Range: -1.5086

Max Act: 1.1300. Min Act: -0.0000

Data Index: 1285378 (C4 (Web Text))

Max Activating Token Index: 614

Text #16

Max Range: 1.5086. Min Range: -1.5086

Max Act: 1.1210. Min Act: -0.0000

Data Index: 1445589 (Python Code)

Max Activating Token Index: 686

Text #17

Max Range: 1.5086. Min Range: -1.5086

Max Act: 1.0767. Min Act: -0.0000

Data Index: 984338 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 1.5086. Min Range: -1.5086

Max Act: 0.9044. Min Act: -0.0000

Data Index: 438838 (C4 (Web Text))

Max Activating Token Index: 306

Text #19

Max Range: 1.5086. Min Range: -1.5086

Max Act: 1.0003. Min Act: -0.0000

Data Index: 1596077 (Python Code)

Max Activating Token Index: 303