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

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

Neuron 4812 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: 2.6928. Min Range: -2.6928

Max Act: 2.6325. Min Act: -0.0000

Data Index: 1517909 (Python Code)

Max Activating Token Index: 649

Text #1

Max Range: 2.6928. Min Range: -2.6928

Max Act: 2.5928. Min Act: -0.0000

Data Index: 1493711 (Python Code)

Max Activating Token Index: 543

Text #2

Max Range: 2.6928. Min Range: -2.6928

Max Act: 2.6928. Min Act: -0.0000

Data Index: 1647576 (Python Code)

Max Activating Token Index: 822

Text #3

Max Range: 2.6928. Min Range: -2.6928

Max Act: 2.5815. Min Act: -0.0000

Data Index: 1631633 (Python Code)

Max Activating Token Index: 520

Text #4

Max Range: 2.6928. Min Range: -2.6928

Max Act: 2.5014. Min Act: -0.0000

Data Index: 1503464 (Python Code)

Max Activating Token Index: 672

Text #5

Max Range: 2.6928. Min Range: -2.6928

Max Act: 2.3640. Min Act: -0.0000

Data Index: 1513850 (Python Code)

Max Activating Token Index: 988

Text #6

Max Range: 2.6928. Min Range: -2.6928

Max Act: 2.0832. Min Act: -0.0000

Data Index: 1533592 (Python Code)

Max Activating Token Index: 447

Text #7

Max Range: 2.6928. Min Range: -2.6928

Max Act: 2.1861. Min Act: -0.0000

Data Index: 1595298 (Python Code)

Max Activating Token Index: 703

Text #8

Max Range: 2.6928. Min Range: -2.6928

Max Act: 2.1417. Min Act: -0.0000

Data Index: 1570739 (Python Code)

Max Activating Token Index: 986

Text #9

Max Range: 2.6928. Min Range: -2.6928

Max Act: 2.0662. Min Act: -0.0000

Data Index: 1452815 (Python Code)

Max Activating Token Index: 344

Text #10

Max Range: 2.6928. Min Range: -2.6928

Max Act: 1.8278. Min Act: -0.0000

Data Index: 1365186 (Python Code)

Max Activating Token Index: 944

Text #11

Max Range: 2.6928. Min Range: -2.6928

Max Act: 1.8995. Min Act: -0.0000

Data Index: 1426531 (Python Code)

Max Activating Token Index: 304

Text #12

Max Range: 2.6928. Min Range: -2.6928

Max Act: 1.8624. Min Act: -0.0000

Data Index: 1601701 (Python Code)

Max Activating Token Index: 759

Text #13

Max Range: 2.6928. Min Range: -2.6928

Max Act: 2.0674. Min Act: -0.0000

Data Index: 1455345 (Python Code)

Max Activating Token Index: 528

Text #14

Max Range: 2.6928. Min Range: -2.6928

Max Act: 1.8283. Min Act: 0.0000

Data Index: 1363238 (Python Code)

Max Activating Token Index: 640

Text #15

Max Range: 2.6928. Min Range: -2.6928

Max Act: 1.8688. Min Act: -0.0000

Data Index: 1462821 (Python Code)

Max Activating Token Index: 288

Text #16

Max Range: 2.6928. Min Range: -2.6928

Max Act: 1.7985. Min Act: -0.0000

Data Index: 1597664 (Python Code)

Max Activating Token Index: 583

Text #17

Max Range: 2.6928. Min Range: -2.6928

Max Act: 1.7934. Min Act: -0.0000

Data Index: 1616139 (Python Code)

Max Activating Token Index: 534

Text #18

Max Range: 2.6928. Min Range: -2.6928

Max Act: 1.6907. Min Act: -0.0000

Data Index: 1592907 (Python Code)

Max Activating Token Index: 936

Text #19

Max Range: 2.6928. Min Range: -2.6928

Max Act: 1.7563. Min Act: -0.0000

Data Index: 1450924 (Python Code)

Max Activating Token Index: 119