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

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

Neuron 1855 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: 0.2005. Min Range: -0.2005

Max Act: 0.2005. Min Act: -0.0002

Data Index: 1189714 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1972. Min Act: -0.0002

Data Index: 1062925 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1894. Min Act: -0.0002

Data Index: 697370 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1836. Min Act: -0.0002

Data Index: 260623 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1847. Min Act: -0.0002

Data Index: 720704 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1873. Min Act: -0.0002

Data Index: 60782 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1834. Min Act: -0.0002

Data Index: 460928 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1844. Min Act: -0.0002

Data Index: 315857 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1799. Min Act: -0.0002

Data Index: 505342 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1747. Min Act: -0.0002

Data Index: 868235 (C4 (Web Text))

Max Activating Token Index: 495

Text #10

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1731. Min Act: -0.0002

Data Index: 115557 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1760. Min Act: -0.0002

Data Index: 908336 (C4 (Web Text))

Max Activating Token Index: 801

Text #12

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1699. Min Act: -0.0002

Data Index: 647598 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1683. Min Act: -0.0002

Data Index: 1578736 (Python Code)

Max Activating Token Index: 823

Text #14

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1686. Min Act: -0.0002

Data Index: 793243 (C4 (Web Text))

Max Activating Token Index: 669

Text #15

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1711. Min Act: -0.0002

Data Index: 1344532 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1702. Min Act: -0.0002

Data Index: 269391 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1705. Min Act: -0.0002

Data Index: 186387 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1701. Min Act: -0.0002

Data Index: 846837 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1693. Min Act: -0.0002

Data Index: 1316753 (C4 (Web Text))

Max Activating Token Index: 2