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

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

Neuron 2707 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: 5.6898. Min Range: -5.6898

Max Act: 5.6898. Min Act: -0.0000

Data Index: 1399732 (Python Code)

Max Activating Token Index: 945

Text #1

Max Range: 5.6898. Min Range: -5.6898

Max Act: 5.2149. Min Act: -0.0000

Data Index: 1432136 (Python Code)

Max Activating Token Index: 964

Text #2

Max Range: 5.6898. Min Range: -5.6898

Max Act: 5.1997. Min Act: -0.0000

Data Index: 1543971 (Python Code)

Max Activating Token Index: 908

Text #3

Max Range: 5.6898. Min Range: -5.6898

Max Act: 5.3212. Min Act: -0.0000

Data Index: 1539102 (Python Code)

Max Activating Token Index: 596

Text #4

Max Range: 5.6898. Min Range: -5.6898

Max Act: 5.2641. Min Act: -0.0000

Data Index: 1389894 (Python Code)

Max Activating Token Index: 321

Text #5

Max Range: 5.6898. Min Range: -5.6898

Max Act: 5.3873. Min Act: -0.0000

Data Index: 1406915 (Python Code)

Max Activating Token Index: 899

Text #6

Max Range: 5.6898. Min Range: -5.6898

Max Act: 5.1351. Min Act: -0.0000

Data Index: 1471755 (Python Code)

Max Activating Token Index: 781

Text #7

Max Range: 5.6898. Min Range: -5.6898

Max Act: 4.9454. Min Act: -0.0000

Data Index: 1652798 (Python Code)

Max Activating Token Index: 745

Text #8

Max Range: 5.6898. Min Range: -5.6898

Max Act: 5.0492. Min Act: -0.0000

Data Index: 1447687 (Python Code)

Max Activating Token Index: 939

Text #9

Max Range: 5.6898. Min Range: -5.6898

Max Act: 5.2219. Min Act: -0.0000

Data Index: 1430103 (Python Code)

Max Activating Token Index: 442

Text #10

Max Range: 5.6898. Min Range: -5.6898

Max Act: 5.0742. Min Act: -0.0000

Data Index: 1376584 (Python Code)

Max Activating Token Index: 935

Text #11

Max Range: 5.6898. Min Range: -5.6898

Max Act: 4.8038. Min Act: -0.0000

Data Index: 1616992 (Python Code)

Max Activating Token Index: 759

Text #12

Max Range: 5.6898. Min Range: -5.6898

Max Act: 4.7770. Min Act: -0.0000

Data Index: 1418989 (Python Code)

Max Activating Token Index: 874

Text #13

Max Range: 5.6898. Min Range: -5.6898

Max Act: 5.0837. Min Act: -0.0000

Data Index: 1540033 (Python Code)

Max Activating Token Index: 787

Text #14

Max Range: 5.6898. Min Range: -5.6898

Max Act: 4.8979. Min Act: -0.0000

Data Index: 1548934 (Python Code)

Max Activating Token Index: 789

Text #15

Max Range: 5.6898. Min Range: -5.6898

Max Act: 4.8567. Min Act: -0.0000

Data Index: 1544305 (Python Code)

Max Activating Token Index: 893

Text #16

Max Range: 5.6898. Min Range: -5.6898

Max Act: 4.8932. Min Act: -0.0000

Data Index: 1624395 (Python Code)

Max Activating Token Index: 953

Text #17

Max Range: 5.6898. Min Range: -5.6898

Max Act: 4.6908. Min Act: -0.0000

Data Index: 1626306 (Python Code)

Max Activating Token Index: 911

Text #18

Max Range: 5.6898. Min Range: -5.6898

Max Act: 4.6692. Min Act: -0.0000

Data Index: 1562742 (Python Code)

Max Activating Token Index: 959

Text #19

Max Range: 5.6898. Min Range: -5.6898

Max Act: 4.7487. Min Act: -0.0000

Data Index: 1615280 (Python Code)

Max Activating Token Index: 980