Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1810 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1953. Min Act: -0.0003

Data Index: 1638583 (Python Code)

Max Activating Token Index: 960

Text #1

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1941. Min Act: -0.0003

Data Index: 1552015 (Python Code)

Max Activating Token Index: 847

Text #2

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1885. Min Act: -0.0003

Data Index: 1390777 (Python Code)

Max Activating Token Index: 1022

Text #3

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.2040. Min Act: -0.0003

Data Index: 1362996 (Python Code)

Max Activating Token Index: 1013

Text #4

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1965. Min Act: -0.0003

Data Index: 1570065 (Python Code)

Max Activating Token Index: 932

Text #5

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1896. Min Act: -0.0003

Data Index: 1396828 (Python Code)

Max Activating Token Index: 892

Text #6

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.2010. Min Act: -0.0003

Data Index: 1628593 (Python Code)

Max Activating Token Index: 959

Text #7

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1948. Min Act: -0.0003

Data Index: 1536906 (Python Code)

Max Activating Token Index: 895

Text #8

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1861. Min Act: -0.0003

Data Index: 1608920 (Python Code)

Max Activating Token Index: 541

Text #9

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1851. Min Act: -0.0003

Data Index: 1540412 (Python Code)

Max Activating Token Index: 311

Text #10

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1889. Min Act: -0.0003

Data Index: 1586957 (Python Code)

Max Activating Token Index: 1007

Text #11

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1891. Min Act: -0.0003

Data Index: 1429413 (Python Code)

Max Activating Token Index: 978

Text #12

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1815. Min Act: -0.0003

Data Index: 1395360 (Python Code)

Max Activating Token Index: 723

Text #13

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1881. Min Act: -0.0003

Data Index: 1548123 (Python Code)

Max Activating Token Index: 784

Text #14

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1881. Min Act: -0.0003

Data Index: 1653977 (Python Code)

Max Activating Token Index: 813

Text #15

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1827. Min Act: -0.0003

Data Index: 1410346 (Python Code)

Max Activating Token Index: 841

Text #16

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1875. Min Act: -0.0003

Data Index: 1517290 (Python Code)

Max Activating Token Index: 808

Text #17

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1873. Min Act: -0.0003

Data Index: 1522228 (Python Code)

Max Activating Token Index: 668

Text #18

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1859. Min Act: -0.0003

Data Index: 1652323 (Python Code)

Max Activating Token Index: 177

Text #19

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1795. Min Act: -0.0003

Data Index: 1516858 (Python Code)

Max Activating Token Index: 712