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

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

Neuron 5530 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.3556. Min Act: -0.0000

Data Index: 1594231 (Python Code)

Max Activating Token Index: 802

Text #1

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.0847. Min Act: -0.0000

Data Index: 1490875 (Python Code)

Max Activating Token Index: 775

Text #2

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.2125. Min Act: -0.0000

Data Index: 1406303 (Python Code)

Max Activating Token Index: 345

Text #3

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.1882. Min Act: -0.0000

Data Index: 1409829 (Python Code)

Max Activating Token Index: 251

Text #4

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.0763. Min Act: -0.0000

Data Index: 1578382 (Python Code)

Max Activating Token Index: 974

Text #5

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.0604. Min Act: -0.0000

Data Index: 1654421 (Python Code)

Max Activating Token Index: 821

Text #6

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.0455. Min Act: -0.0000

Data Index: 1392618 (Python Code)

Max Activating Token Index: 555

Text #7

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.0709. Min Act: -0.0000

Data Index: 1538919 (Python Code)

Max Activating Token Index: 863

Text #8

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.0663. Min Act: -0.0000

Data Index: 1406355 (Python Code)

Max Activating Token Index: 669

Text #9

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.0581. Min Act: -0.0000

Data Index: 1588095 (Python Code)

Max Activating Token Index: 41

Text #10

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.0430. Min Act: -0.0000

Data Index: 1556557 (Python Code)

Max Activating Token Index: 131

Text #11

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.0337. Min Act: -0.0000

Data Index: 1563820 (Python Code)

Max Activating Token Index: 59

Text #12

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.0077. Min Act: -0.0000

Data Index: 1641460 (Python Code)

Max Activating Token Index: 905

Text #13

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.0744. Min Act: -0.0000

Data Index: 1369095 (Python Code)

Max Activating Token Index: 860

Text #14

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.0027. Min Act: -0.0000

Data Index: 1462354 (Python Code)

Max Activating Token Index: 456

Text #15

Max Range: 1.3556. Min Range: -1.3556

Max Act: 0.9767. Min Act: -0.0000

Data Index: 1417609 (Python Code)

Max Activating Token Index: 985

Text #16

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.0336. Min Act: -0.0000

Data Index: 1634693 (Python Code)

Max Activating Token Index: 795

Text #17

Max Range: 1.3556. Min Range: -1.3556

Max Act: 0.9383. Min Act: -0.0000

Data Index: 1632331 (Python Code)

Max Activating Token Index: 509

Text #18

Max Range: 1.3556. Min Range: -1.3556

Max Act: 0.8862. Min Act: -0.0000

Data Index: 1407869 (Python Code)

Max Activating Token Index: 886

Text #19

Max Range: 1.3556. Min Range: -1.3556

Max Act: 0.9448. Min Act: -0.0000

Data Index: 1557733 (Python Code)

Max Activating Token Index: 989