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

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

Neuron 2882 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2632. Min Act: -0.0000

Data Index: 169959 (C4 (Web Text))

Max Activating Token Index: 344

Text #1

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2357. Min Act: -0.0000

Data Index: 464670 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2282. Min Act: -0.0000

Data Index: 1364232 (Python Code)

Max Activating Token Index: 510

Text #3

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2061. Min Act: -0.0000

Data Index: 1428413 (Python Code)

Max Activating Token Index: 474

Text #4

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2162. Min Act: -0.0000

Data Index: 518642 (C4 (Web Text))

Max Activating Token Index: 996

Text #5

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.1915. Min Act: -0.0000

Data Index: 1379890 (Python Code)

Max Activating Token Index: 462

Text #6

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.1847. Min Act: -0.0000

Data Index: 1537595 (Python Code)

Max Activating Token Index: 721

Text #7

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.1857. Min Act: -0.0000

Data Index: 1598472 (Python Code)

Max Activating Token Index: 785

Text #8

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2033. Min Act: -0.0000

Data Index: 771337 (C4 (Web Text))

Max Activating Token Index: 686

Text #9

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.1837. Min Act: -0.0000

Data Index: 918057 (C4 (Web Text))

Max Activating Token Index: 625

Text #10

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.1662. Min Act: -0.0000

Data Index: 1514451 (Python Code)

Max Activating Token Index: 711

Text #11

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.1713. Min Act: -0.0000

Data Index: 1440727 (Python Code)

Max Activating Token Index: 840

Text #12

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.1765. Min Act: -0.0000

Data Index: 1184386 (C4 (Web Text))

Max Activating Token Index: 572

Text #13

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.1692. Min Act: -0.0000

Data Index: 1420558 (Python Code)

Max Activating Token Index: 333

Text #14

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.1739. Min Act: -0.0000

Data Index: 940176 (C4 (Web Text))

Max Activating Token Index: 653

Text #15

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.1848. Min Act: -0.0000

Data Index: 1458800 (Python Code)

Max Activating Token Index: 172

Text #16

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.1707. Min Act: -0.0000

Data Index: 1650861 (Python Code)

Max Activating Token Index: 325

Text #17

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.1648. Min Act: -0.0000

Data Index: 1452611 (Python Code)

Max Activating Token Index: 870

Text #18

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.1578. Min Act: -0.0000

Data Index: 1536718 (Python Code)

Max Activating Token Index: 205

Text #19

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.1520. Min Act: -0.0000

Data Index: 268361 (C4 (Web Text))

Max Activating Token Index: 515