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

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

Neuron 919 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7894. Min Range: -3.7894

Max Act: 3.7894. Min Act: -0.0000

Data Index: 1566547 (Python Code)

Max Activating Token Index: 934

Text #1

Max Range: 3.7894. Min Range: -3.7894

Max Act: 3.4709. Min Act: -0.0000

Data Index: 1440009 (Python Code)

Max Activating Token Index: 618

Text #2

Max Range: 3.7894. Min Range: -3.7894

Max Act: 3.4289. Min Act: -0.0000

Data Index: 1585220 (Python Code)

Max Activating Token Index: 994

Text #3

Max Range: 3.7894. Min Range: -3.7894

Max Act: 3.2736. Min Act: -0.0000

Data Index: 1570200 (Python Code)

Max Activating Token Index: 739

Text #4

Max Range: 3.7894. Min Range: -3.7894

Max Act: 3.1426. Min Act: -0.0000

Data Index: 1598573 (Python Code)

Max Activating Token Index: 995

Text #5

Max Range: 3.7894. Min Range: -3.7894

Max Act: 3.4572. Min Act: -0.0000

Data Index: 1581161 (Python Code)

Max Activating Token Index: 857

Text #6

Max Range: 3.7894. Min Range: -3.7894

Max Act: 3.3816. Min Act: -0.0000

Data Index: 1513258 (Python Code)

Max Activating Token Index: 971

Text #7

Max Range: 3.7894. Min Range: -3.7894

Max Act: 3.0732. Min Act: -0.0000

Data Index: 1548615 (Python Code)

Max Activating Token Index: 842

Text #8

Max Range: 3.7894. Min Range: -3.7894

Max Act: 3.0658. Min Act: -0.0000

Data Index: 1638826 (Python Code)

Max Activating Token Index: 244

Text #9

Max Range: 3.7894. Min Range: -3.7894

Max Act: 3.1710. Min Act: -0.0000

Data Index: 1447439 (Python Code)

Max Activating Token Index: 1001

Text #10

Max Range: 3.7894. Min Range: -3.7894

Max Act: 3.1597. Min Act: -0.0000

Data Index: 1558539 (Python Code)

Max Activating Token Index: 909

Text #11

Max Range: 3.7894. Min Range: -3.7894

Max Act: 3.1592. Min Act: -0.0000

Data Index: 1609774 (Python Code)

Max Activating Token Index: 1011

Text #12

Max Range: 3.7894. Min Range: -3.7894

Max Act: 3.1493. Min Act: -0.0000

Data Index: 1533208 (Python Code)

Max Activating Token Index: 922

Text #13

Max Range: 3.7894. Min Range: -3.7894

Max Act: 3.2971. Min Act: -0.0000

Data Index: 1475894 (Python Code)

Max Activating Token Index: 870

Text #14

Max Range: 3.7894. Min Range: -3.7894

Max Act: 3.2840. Min Act: -0.0000

Data Index: 1638927 (Python Code)

Max Activating Token Index: 974

Text #15

Max Range: 3.7894. Min Range: -3.7894

Max Act: 3.1436. Min Act: -0.0000

Data Index: 1515177 (Python Code)

Max Activating Token Index: 816

Text #16

Max Range: 3.7894. Min Range: -3.7894

Max Act: 3.3132. Min Act: -0.0000

Data Index: 1362695 (Python Code)

Max Activating Token Index: 884

Text #17

Max Range: 3.7894. Min Range: -3.7894

Max Act: 3.1586. Min Act: -0.0000

Data Index: 1633844 (Python Code)

Max Activating Token Index: 884

Text #18

Max Range: 3.7894. Min Range: -3.7894

Max Act: 3.0047. Min Act: -0.0000

Data Index: 1389326 (Python Code)

Max Activating Token Index: 812

Text #19

Max Range: 3.7894. Min Range: -3.7894

Max Act: 3.2397. Min Act: -0.0000

Data Index: 1653183 (Python Code)

Max Activating Token Index: 305