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

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

Neuron 6134 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: 0.1894. Min Range: -0.1894

Max Act: 0.1894. Min Act: -0.0002

Data Index: 1534059 (Python Code)

Max Activating Token Index: 863

Text #1

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1842. Min Act: -0.0002

Data Index: 1575271 (Python Code)

Max Activating Token Index: 816

Text #2

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1855. Min Act: -0.0002

Data Index: 1602475 (Python Code)

Max Activating Token Index: 862

Text #3

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1839. Min Act: -0.0002

Data Index: 1559347 (Python Code)

Max Activating Token Index: 913

Text #4

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1784. Min Act: -0.0002

Data Index: 1456746 (Python Code)

Max Activating Token Index: 830

Text #5

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1830. Min Act: -0.0002

Data Index: 1511120 (Python Code)

Max Activating Token Index: 1004

Text #6

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1797. Min Act: -0.0002

Data Index: 1407712 (Python Code)

Max Activating Token Index: 782

Text #7

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1783. Min Act: -0.0002

Data Index: 1373137 (Python Code)

Max Activating Token Index: 850

Text #8

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1737. Min Act: -0.0002

Data Index: 1454648 (Python Code)

Max Activating Token Index: 678

Text #9

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1764. Min Act: -0.0002

Data Index: 1569552 (Python Code)

Max Activating Token Index: 745

Text #10

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1718. Min Act: -0.0002

Data Index: 1368687 (Python Code)

Max Activating Token Index: 543

Text #11

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1692. Min Act: -0.0002

Data Index: 1515061 (Python Code)

Max Activating Token Index: 912

Text #12

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1751. Min Act: -0.0002

Data Index: 1510002 (Python Code)

Max Activating Token Index: 716

Text #13

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1717. Min Act: -0.0002

Data Index: 1438622 (Python Code)

Max Activating Token Index: 302

Text #14

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1693. Min Act: -0.0002

Data Index: 1479615 (Python Code)

Max Activating Token Index: 605

Text #15

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1663. Min Act: -0.0002

Data Index: 1370039 (Python Code)

Max Activating Token Index: 758

Text #16

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1673. Min Act: -0.0002

Data Index: 1606842 (Python Code)

Max Activating Token Index: 259

Text #17

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1702. Min Act: -0.0002

Data Index: 1592650 (Python Code)

Max Activating Token Index: 383

Text #18

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1698. Min Act: -0.0002

Data Index: 1470544 (Python Code)

Max Activating Token Index: 1009

Text #19

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1694. Min Act: -0.0002

Data Index: 1427918 (Python Code)

Max Activating Token Index: 820