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

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

Neuron 3522 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5935. Min Range: -1.5935

Max Act: 1.5935. Min Act: -0.0000

Data Index: 1558454 (Python Code)

Max Activating Token Index: 542

Text #1

Max Range: 1.5935. Min Range: -1.5935

Max Act: 1.4666. Min Act: -0.0000

Data Index: 1436313 (Python Code)

Max Activating Token Index: 222

Text #2

Max Range: 1.5935. Min Range: -1.5935

Max Act: 1.5129. Min Act: -0.0000

Data Index: 1537180 (Python Code)

Max Activating Token Index: 701

Text #3

Max Range: 1.5935. Min Range: -1.5935

Max Act: 1.4521. Min Act: -0.0000

Data Index: 1626775 (Python Code)

Max Activating Token Index: 524

Text #4

Max Range: 1.5935. Min Range: -1.5935

Max Act: 1.4742. Min Act: -0.0000

Data Index: 1377883 (Python Code)

Max Activating Token Index: 594

Text #5

Max Range: 1.5935. Min Range: -1.5935

Max Act: 1.4418. Min Act: -0.0000

Data Index: 1557497 (Python Code)

Max Activating Token Index: 499

Text #6

Max Range: 1.5935. Min Range: -1.5935

Max Act: 1.4256. Min Act: -0.0000

Data Index: 1375390 (Python Code)

Max Activating Token Index: 824

Text #7

Max Range: 1.5935. Min Range: -1.5935

Max Act: 1.3619. Min Act: -0.0000

Data Index: 1558988 (Python Code)

Max Activating Token Index: 494

Text #8

Max Range: 1.5935. Min Range: -1.5935

Max Act: 1.2693. Min Act: -0.0000

Data Index: 1401160 (Python Code)

Max Activating Token Index: 731

Text #9

Max Range: 1.5935. Min Range: -1.5935

Max Act: 1.1984. Min Act: -0.0000

Data Index: 1428106 (Python Code)

Max Activating Token Index: 520

Text #10

Max Range: 1.5935. Min Range: -1.5935

Max Act: 1.2294. Min Act: -0.0000

Data Index: 1376237 (Python Code)

Max Activating Token Index: 956

Text #11

Max Range: 1.5935. Min Range: -1.5935

Max Act: 1.1278. Min Act: -0.0000

Data Index: 1482539 (Python Code)

Max Activating Token Index: 553

Text #12

Max Range: 1.5935. Min Range: -1.5935

Max Act: 1.1625. Min Act: -0.0000

Data Index: 1579629 (Python Code)

Max Activating Token Index: 624

Text #13

Max Range: 1.5935. Min Range: -1.5935

Max Act: 1.1981. Min Act: -0.0000

Data Index: 1537740 (Python Code)

Max Activating Token Index: 817

Text #14

Max Range: 1.5935. Min Range: -1.5935

Max Act: 1.1995. Min Act: -0.0000

Data Index: 1482680 (Python Code)

Max Activating Token Index: 723

Text #15

Max Range: 1.5935. Min Range: -1.5935

Max Act: 1.1199. Min Act: -0.0000

Data Index: 1516039 (Python Code)

Max Activating Token Index: 637

Text #16

Max Range: 1.5935. Min Range: -1.5935

Max Act: 1.1688. Min Act: -0.0000

Data Index: 1561518 (Python Code)

Max Activating Token Index: 62

Text #17

Max Range: 1.5935. Min Range: -1.5935

Max Act: 1.1223. Min Act: -0.0000

Data Index: 1541472 (Python Code)

Max Activating Token Index: 829

Text #18

Max Range: 1.5935. Min Range: -1.5935

Max Act: 1.0977. Min Act: -0.0000

Data Index: 1563180 (Python Code)

Max Activating Token Index: 249

Text #19

Max Range: 1.5935. Min Range: -1.5935

Max Act: 1.1646. Min Act: -0.0000

Data Index: 1480429 (Python Code)

Max Activating Token Index: 999