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

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

Neuron 5840 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.3677. Min Act: -0.0000

Data Index: 1364170 (Python Code)

Max Activating Token Index: 123

Text #1

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.3633. Min Act: -0.0000

Data Index: 1576334 (Python Code)

Max Activating Token Index: 678

Text #2

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.3357. Min Act: -0.0000

Data Index: 1549869 (Python Code)

Max Activating Token Index: 761

Text #3

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.3581. Min Act: -0.0000

Data Index: 1541733 (Python Code)

Max Activating Token Index: 762

Text #4

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.3200. Min Act: -0.0000

Data Index: 1462936 (Python Code)

Max Activating Token Index: 100

Text #5

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.3150. Min Act: -0.0000

Data Index: 1507121 (Python Code)

Max Activating Token Index: 574

Text #6

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.3098. Min Act: -0.0000

Data Index: 1456145 (Python Code)

Max Activating Token Index: 752

Text #7

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.3076. Min Act: -0.0000

Data Index: 1638778 (Python Code)

Max Activating Token Index: 548

Text #8

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.2970. Min Act: -0.0000

Data Index: 1413853 (Python Code)

Max Activating Token Index: 367

Text #9

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.3035. Min Act: -0.0000

Data Index: 1652485 (Python Code)

Max Activating Token Index: 914

Text #10

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.3463. Min Act: -0.0000

Data Index: 1556119 (Python Code)

Max Activating Token Index: 655

Text #11

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.3082. Min Act: -0.0000

Data Index: 1499903 (Python Code)

Max Activating Token Index: 383

Text #12

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.3004. Min Act: -0.0000

Data Index: 1414975 (Python Code)

Max Activating Token Index: 192

Text #13

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.2836. Min Act: -0.0000

Data Index: 1635090 (Python Code)

Max Activating Token Index: 433

Text #14

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.3026. Min Act: 0.0000

Data Index: 658179 (C4 (Web Text))

Max Activating Token Index: 44

Text #15

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.2797. Min Act: -0.0000

Data Index: 1614444 (Python Code)

Max Activating Token Index: 116

Text #16

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.2861. Min Act: -0.0000

Data Index: 1648295 (Python Code)

Max Activating Token Index: 337

Text #17

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.2865. Min Act: -0.0000

Data Index: 721571 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.2836. Min Act: -0.0000

Data Index: 433462 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.2902. Min Act: -0.0000

Data Index: 1606634 (Python Code)

Max Activating Token Index: 824