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

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

Neuron 4419 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9528. Min Range: -1.9528

Max Act: 1.9528. Min Act: -0.0000

Data Index: 1360451 (Python Code)

Max Activating Token Index: 635

Text #1

Max Range: 1.9528. Min Range: -1.9528

Max Act: 1.5503. Min Act: -0.0000

Data Index: 1577402 (Python Code)

Max Activating Token Index: 477

Text #2

Max Range: 1.9528. Min Range: -1.9528

Max Act: 1.5373. Min Act: -0.0000

Data Index: 1412839 (Python Code)

Max Activating Token Index: 994

Text #3

Max Range: 1.9528. Min Range: -1.9528

Max Act: 1.4262. Min Act: -0.0000

Data Index: 1529355 (Python Code)

Max Activating Token Index: 876

Text #4

Max Range: 1.9528. Min Range: -1.9528

Max Act: 1.4669. Min Act: -0.0000

Data Index: 1003453 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 1.9528. Min Range: -1.9528

Max Act: 1.3333. Min Act: -0.0000

Data Index: 1460704 (Python Code)

Max Activating Token Index: 133

Text #6

Max Range: 1.9528. Min Range: -1.9528

Max Act: 1.3704. Min Act: -0.0000

Data Index: 1594980 (Python Code)

Max Activating Token Index: 89

Text #7

Max Range: 1.9528. Min Range: -1.9528

Max Act: 1.3396. Min Act: -0.0000

Data Index: 1407884 (Python Code)

Max Activating Token Index: 152

Text #8

Max Range: 1.9528. Min Range: -1.9528

Max Act: 1.3940. Min Act: -0.0000

Data Index: 1370020 (Python Code)

Max Activating Token Index: 170

Text #9

Max Range: 1.9528. Min Range: -1.9528

Max Act: 1.2771. Min Act: -0.0000

Data Index: 1508109 (Python Code)

Max Activating Token Index: 798

Text #10

Max Range: 1.9528. Min Range: -1.9528

Max Act: 1.2650. Min Act: -0.0000

Data Index: 1543267 (Python Code)

Max Activating Token Index: 721

Text #11

Max Range: 1.9528. Min Range: -1.9528

Max Act: 1.3655. Min Act: -0.0000

Data Index: 1583992 (Python Code)

Max Activating Token Index: 694

Text #12

Max Range: 1.9528. Min Range: -1.9528

Max Act: 1.2220. Min Act: -0.0000

Data Index: 1566529 (Python Code)

Max Activating Token Index: 318

Text #13

Max Range: 1.9528. Min Range: -1.9528

Max Act: 1.1801. Min Act: -0.0000

Data Index: 1541824 (Python Code)

Max Activating Token Index: 460

Text #14

Max Range: 1.9528. Min Range: -1.9528

Max Act: 1.2797. Min Act: -0.0000

Data Index: 1360883 (Python Code)

Max Activating Token Index: 304

Text #15

Max Range: 1.9528. Min Range: -1.9528

Max Act: 1.1714. Min Act: -0.0000

Data Index: 1413737 (Python Code)

Max Activating Token Index: 997

Text #16

Max Range: 1.9528. Min Range: -1.9528

Max Act: 1.1877. Min Act: -0.0000

Data Index: 1458439 (Python Code)

Max Activating Token Index: 70

Text #17

Max Range: 1.9528. Min Range: -1.9528

Max Act: 1.1172. Min Act: -0.0000

Data Index: 1467188 (Python Code)

Max Activating Token Index: 826

Text #18

Max Range: 1.9528. Min Range: -1.9528

Max Act: 1.0116. Min Act: -0.0000

Data Index: 1366275 (Python Code)

Max Activating Token Index: 650

Text #19

Max Range: 1.9528. Min Range: -1.9528

Max Act: 1.1126. Min Act: -0.0000

Data Index: 1553673 (Python Code)

Max Activating Token Index: 12