Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 412 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4035. Min Range: -0.4035

Max Act: 0.4035. Min Act: -0.0000

Data Index: 1410344 (Python Code)

Max Activating Token Index: 71

Text #1

Max Range: 0.4035. Min Range: -0.4035

Max Act: 0.3693. Min Act: -0.0000

Data Index: 1392253 (Python Code)

Max Activating Token Index: 1006

Text #2

Max Range: 0.4035. Min Range: -0.4035

Max Act: 0.3692. Min Act: -0.0000

Data Index: 1533005 (Python Code)

Max Activating Token Index: 26

Text #3

Max Range: 0.4035. Min Range: -0.4035

Max Act: 0.3598. Min Act: 0.0000

Data Index: 1631831 (Python Code)

Max Activating Token Index: 922

Text #4

Max Range: 0.4035. Min Range: -0.4035

Max Act: 0.3340. Min Act: 0.0000

Data Index: 1453770 (Python Code)

Max Activating Token Index: 191

Text #5

Max Range: 0.4035. Min Range: -0.4035

Max Act: 0.2823. Min Act: -0.0000

Data Index: 1640141 (Python Code)

Max Activating Token Index: 570

Text #6

Max Range: 0.4035. Min Range: -0.4035

Max Act: 0.2936. Min Act: 0.0001

Data Index: 1625460 (Python Code)

Max Activating Token Index: 616

Text #7

Max Range: 0.4035. Min Range: -0.4035

Max Act: 0.2931. Min Act: -0.0000

Data Index: 1377250 (Python Code)

Max Activating Token Index: 687

Text #8

Max Range: 0.4035. Min Range: -0.4035

Max Act: 0.2881. Min Act: -0.0000

Data Index: 1429111 (Python Code)

Max Activating Token Index: 924

Text #9

Max Range: 0.4035. Min Range: -0.4035

Max Act: 0.2980. Min Act: -0.0000

Data Index: 1629707 (Python Code)

Max Activating Token Index: 399

Text #10

Max Range: 0.4035. Min Range: -0.4035

Max Act: 0.2979. Min Act: -0.0000

Data Index: 1504333 (Python Code)

Max Activating Token Index: 156

Text #11

Max Range: 0.4035. Min Range: -0.4035

Max Act: 0.2865. Min Act: -0.0000

Data Index: 1440499 (Python Code)

Max Activating Token Index: 621

Text #12

Max Range: 0.4035. Min Range: -0.4035

Max Act: 0.2742. Min Act: -0.0000

Data Index: 1601211 (Python Code)

Max Activating Token Index: 31

Text #13

Max Range: 0.4035. Min Range: -0.4035

Max Act: 0.2789. Min Act: -0.0000

Data Index: 1458335 (Python Code)

Max Activating Token Index: 822

Text #14

Max Range: 0.4035. Min Range: -0.4035

Max Act: 0.2764. Min Act: 0.0000

Data Index: 1391600 (Python Code)

Max Activating Token Index: 25

Text #15

Max Range: 0.4035. Min Range: -0.4035

Max Act: 0.2762. Min Act: -0.0000

Data Index: 1495339 (Python Code)

Max Activating Token Index: 567

Text #16

Max Range: 0.4035. Min Range: -0.4035

Max Act: 0.2665. Min Act: 0.0000

Data Index: 1405395 (Python Code)

Max Activating Token Index: 302

Text #17

Max Range: 0.4035. Min Range: -0.4035

Max Act: 0.2747. Min Act: -0.0000

Data Index: 1611570 (Python Code)

Max Activating Token Index: 329

Text #18

Max Range: 0.4035. Min Range: -0.4035

Max Act: 0.2698. Min Act: 0.0000

Data Index: 1505650 (Python Code)

Max Activating Token Index: 450

Text #19

Max Range: 0.4035. Min Range: -0.4035

Max Act: 0.2580. Min Act: 0.0000

Data Index: 1595716 (Python Code)

Max Activating Token Index: 945