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

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

Neuron 4175 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2896. Min Act: -0.0001

Data Index: 1618203 (Python Code)

Max Activating Token Index: 779

Text #1

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2077. Min Act: -0.0001

Data Index: 1453741 (Python Code)

Max Activating Token Index: 447

Text #2

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2211. Min Act: -0.0001

Data Index: 1385435 (Python Code)

Max Activating Token Index: 466

Text #3

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2119. Min Act: -0.0001

Data Index: 1364882 (Python Code)

Max Activating Token Index: 687

Text #4

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.1983. Min Act: -0.0001

Data Index: 1598007 (Python Code)

Max Activating Token Index: 456

Text #5

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.1855. Min Act: -0.0001

Data Index: 1606783 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.1857. Min Act: -0.0001

Data Index: 1404555 (Python Code)

Max Activating Token Index: 727

Text #7

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.1937. Min Act: -0.0001

Data Index: 1647693 (Python Code)

Max Activating Token Index: 892

Text #8

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.1860. Min Act: -0.0001

Data Index: 1504471 (Python Code)

Max Activating Token Index: 1021

Text #9

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.1805. Min Act: -0.0001

Data Index: 1517027 (Python Code)

Max Activating Token Index: 673

Text #10

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.1731. Min Act: -0.0001

Data Index: 1443712 (Python Code)

Max Activating Token Index: 338

Text #11

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.1618. Min Act: -0.0001

Data Index: 1397499 (Python Code)

Max Activating Token Index: 631

Text #12

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.1800. Min Act: -0.0001

Data Index: 1487849 (Python Code)

Max Activating Token Index: 896

Text #13

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.1846. Min Act: -0.0001

Data Index: 1386296 (Python Code)

Max Activating Token Index: 718

Text #14

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.1697. Min Act: -0.0001

Data Index: 1497162 (Python Code)

Max Activating Token Index: 456

Text #15

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.1819. Min Act: -0.0001

Data Index: 1442796 (Python Code)

Max Activating Token Index: 732

Text #16

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.1651. Min Act: -0.0001

Data Index: 1361553 (Python Code)

Max Activating Token Index: 295

Text #17

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.1676. Min Act: -0.0001

Data Index: 1438380 (Python Code)

Max Activating Token Index: 785

Text #18

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.1683. Min Act: -0.0001

Data Index: 1546031 (Python Code)

Max Activating Token Index: 930

Text #19

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.1533. Min Act: -0.0001

Data Index: 1565327 (Python Code)

Max Activating Token Index: 634