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

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

Neuron 768 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.2061. Min Range: -0.2061

Max Act: 0.2061. Min Act: -0.0002

Data Index: 929826 (C4 (Web Text))

Max Activating Token Index: 679

Text #1

Max Range: 0.2061. Min Range: -0.2061

Max Act: 0.2058. Min Act: -0.0002

Data Index: 1517358 (Python Code)

Max Activating Token Index: 812

Text #2

Max Range: 0.2061. Min Range: -0.2061

Max Act: 0.1992. Min Act: -0.0002

Data Index: 1560878 (Python Code)

Max Activating Token Index: 51

Text #3

Max Range: 0.2061. Min Range: -0.2061

Max Act: 0.1989. Min Act: -0.0002

Data Index: 1541650 (Python Code)

Max Activating Token Index: 12

Text #4

Max Range: 0.2061. Min Range: -0.2061

Max Act: 0.1965. Min Act: -0.0002

Data Index: 1403789 (Python Code)

Max Activating Token Index: 122

Text #5

Max Range: 0.2061. Min Range: -0.2061

Max Act: 0.1900. Min Act: -0.0002

Data Index: 1472917 (Python Code)

Max Activating Token Index: 8

Text #6

Max Range: 0.2061. Min Range: -0.2061

Max Act: 0.1888. Min Act: -0.0002

Data Index: 1424089 (Python Code)

Max Activating Token Index: 643

Text #7

Max Range: 0.2061. Min Range: -0.2061

Max Act: 0.1920. Min Act: -0.0002

Data Index: 1420722 (Python Code)

Max Activating Token Index: 513

Text #8

Max Range: 0.2061. Min Range: -0.2061

Max Act: 0.1905. Min Act: -0.0002

Data Index: 1176458 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 0.2061. Min Range: -0.2061

Max Act: 0.1830. Min Act: -0.0002

Data Index: 1482981 (Python Code)

Max Activating Token Index: 23

Text #10

Max Range: 0.2061. Min Range: -0.2061

Max Act: 0.1844. Min Act: -0.0002

Data Index: 1374075 (Python Code)

Max Activating Token Index: 61

Text #11

Max Range: 0.2061. Min Range: -0.2061

Max Act: 0.1867. Min Act: -0.0002

Data Index: 1157156 (C4 (Web Text))

Max Activating Token Index: 266

Text #12

Max Range: 0.2061. Min Range: -0.2061

Max Act: 0.1840. Min Act: -0.0002

Data Index: 1276290 (C4 (Web Text))

Max Activating Token Index: 718

Text #13

Max Range: 0.2061. Min Range: -0.2061

Max Act: 0.1812. Min Act: -0.0002

Data Index: 1574795 (Python Code)

Max Activating Token Index: 138

Text #14

Max Range: 0.2061. Min Range: -0.2061

Max Act: 0.1823. Min Act: -0.0002

Data Index: 1652693 (Python Code)

Max Activating Token Index: 558

Text #15

Max Range: 0.2061. Min Range: -0.2061

Max Act: 0.1786. Min Act: -0.0002

Data Index: 1401819 (Python Code)

Max Activating Token Index: 289

Text #16

Max Range: 0.2061. Min Range: -0.2061

Max Act: 0.1756. Min Act: -0.0002

Data Index: 1445296 (Python Code)

Max Activating Token Index: 10

Text #17

Max Range: 0.2061. Min Range: -0.2061

Max Act: 0.1780. Min Act: -0.0002

Data Index: 1502822 (Python Code)

Max Activating Token Index: 22

Text #18

Max Range: 0.2061. Min Range: -0.2061

Max Act: 0.1746. Min Act: -0.0002

Data Index: 1480698 (Python Code)

Max Activating Token Index: 562

Text #19

Max Range: 0.2061. Min Range: -0.2061

Max Act: 0.1749. Min Act: -0.0002

Data Index: 564064 (C4 (Web Text))

Max Activating Token Index: 454