Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 92 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.2446. Min Act: -0.0001

Data Index: 1553600 (Python Code)

Max Activating Token Index: 106

Text #1

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.2207. Min Act: -0.0001

Data Index: 1633547 (Python Code)

Max Activating Token Index: 63

Text #2

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.2131. Min Act: -0.0001

Data Index: 1573478 (Python Code)

Max Activating Token Index: 64

Text #3

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.2092. Min Act: -0.0001

Data Index: 1404971 (Python Code)

Max Activating Token Index: 417

Text #4

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1880. Min Act: -0.0001

Data Index: 1398121 (Python Code)

Max Activating Token Index: 233

Text #5

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1873. Min Act: -0.0001

Data Index: 1466148 (Python Code)

Max Activating Token Index: 768

Text #6

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1869. Min Act: -0.0001

Data Index: 1385591 (Python Code)

Max Activating Token Index: 742

Text #7

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1902. Min Act: -0.0001

Data Index: 1636083 (Python Code)

Max Activating Token Index: 30

Text #8

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1608. Min Act: -0.0001

Data Index: 1507815 (Python Code)

Max Activating Token Index: 757

Text #9

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1573. Min Act: -0.0001

Data Index: 1618255 (Python Code)

Max Activating Token Index: 830

Text #10

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1769. Min Act: -0.0001

Data Index: 1484314 (Python Code)

Max Activating Token Index: 613

Text #11

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1653. Min Act: -0.0001

Data Index: 1374699 (Python Code)

Max Activating Token Index: 17

Text #12

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1731. Min Act: -0.0001

Data Index: 1642684 (Python Code)

Max Activating Token Index: 248

Text #13

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1638. Min Act: -0.0001

Data Index: 1437107 (Python Code)

Max Activating Token Index: 709

Text #14

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1667. Min Act: -0.0001

Data Index: 1631072 (Python Code)

Max Activating Token Index: 344

Text #15

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1584. Min Act: -0.0001

Data Index: 1617400 (Python Code)

Max Activating Token Index: 660

Text #16

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1663. Min Act: -0.0001

Data Index: 1462403 (Python Code)

Max Activating Token Index: 849

Text #17

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1599. Min Act: -0.0001

Data Index: 1537372 (Python Code)

Max Activating Token Index: 186

Text #18

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1522. Min Act: -0.0001

Data Index: 1556438 (Python Code)

Max Activating Token Index: 1005

Text #19

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1742. Min Act: -0.0001

Data Index: 1545107 (Python Code)

Max Activating Token Index: 34