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

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

Neuron 3901 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: 2.5797. Min Range: -2.5797

Max Act: 2.5797. Min Act: -0.0000

Data Index: 1558406 (Python Code)

Max Activating Token Index: 918

Text #1

Max Range: 2.5797. Min Range: -2.5797

Max Act: 2.1436. Min Act: -0.0000

Data Index: 1543438 (Python Code)

Max Activating Token Index: 798

Text #2

Max Range: 2.5797. Min Range: -2.5797

Max Act: 2.1868. Min Act: -0.0000

Data Index: 1486531 (Python Code)

Max Activating Token Index: 311

Text #3

Max Range: 2.5797. Min Range: -2.5797

Max Act: 2.2799. Min Act: -0.0000

Data Index: 1497825 (Python Code)

Max Activating Token Index: 124

Text #4

Max Range: 2.5797. Min Range: -2.5797

Max Act: 2.1504. Min Act: -0.0000

Data Index: 1553867 (Python Code)

Max Activating Token Index: 358

Text #5

Max Range: 2.5797. Min Range: -2.5797

Max Act: 2.1100. Min Act: -0.0000

Data Index: 1390815 (Python Code)

Max Activating Token Index: 512

Text #6

Max Range: 2.5797. Min Range: -2.5797

Max Act: 2.0960. Min Act: -0.0000

Data Index: 1526773 (Python Code)

Max Activating Token Index: 169

Text #7

Max Range: 2.5797. Min Range: -2.5797

Max Act: 2.1981. Min Act: -0.0000

Data Index: 1625042 (Python Code)

Max Activating Token Index: 1022

Text #8

Max Range: 2.5797. Min Range: -2.5797

Max Act: 2.0821. Min Act: -0.0000

Data Index: 1422077 (Python Code)

Max Activating Token Index: 90

Text #9

Max Range: 2.5797. Min Range: -2.5797

Max Act: 2.0458. Min Act: -0.0000

Data Index: 1566952 (Python Code)

Max Activating Token Index: 556

Text #10

Max Range: 2.5797. Min Range: -2.5797

Max Act: 2.0457. Min Act: -0.0000

Data Index: 1607219 (Python Code)

Max Activating Token Index: 388

Text #11

Max Range: 2.5797. Min Range: -2.5797

Max Act: 2.0185. Min Act: -0.0000

Data Index: 1560149 (Python Code)

Max Activating Token Index: 911

Text #12

Max Range: 2.5797. Min Range: -2.5797

Max Act: 1.9977. Min Act: -0.0000

Data Index: 1506751 (Python Code)

Max Activating Token Index: 752

Text #13

Max Range: 2.5797. Min Range: -2.5797

Max Act: 2.0630. Min Act: -0.0000

Data Index: 1609876 (Python Code)

Max Activating Token Index: 306

Text #14

Max Range: 2.5797. Min Range: -2.5797

Max Act: 2.0550. Min Act: -0.0000

Data Index: 1571767 (Python Code)

Max Activating Token Index: 604

Text #15

Max Range: 2.5797. Min Range: -2.5797

Max Act: 1.8283. Min Act: -0.0000

Data Index: 1635236 (Python Code)

Max Activating Token Index: 977

Text #16

Max Range: 2.5797. Min Range: -2.5797

Max Act: 1.9252. Min Act: -0.0000

Data Index: 1516330 (Python Code)

Max Activating Token Index: 66

Text #17

Max Range: 2.5797. Min Range: -2.5797

Max Act: 2.0207. Min Act: -0.0000

Data Index: 1476816 (Python Code)

Max Activating Token Index: 294

Text #18

Max Range: 2.5797. Min Range: -2.5797

Max Act: 1.8843. Min Act: -0.0000

Data Index: 1441691 (Python Code)

Max Activating Token Index: 520

Text #19

Max Range: 2.5797. Min Range: -2.5797

Max Act: 1.7674. Min Act: -0.0000

Data Index: 1609682 (Python Code)

Max Activating Token Index: 294