Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4477 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2595. Min Act: -0.0000

Data Index: 1424076 (Python Code)

Max Activating Token Index: 866

Text #1

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2506. Min Act: -0.0000

Data Index: 1582035 (Python Code)

Max Activating Token Index: 654

Text #2

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2225. Min Act: -0.0000

Data Index: 1629967 (Python Code)

Max Activating Token Index: 669

Text #3

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2082. Min Act: -0.0000

Data Index: 1552621 (Python Code)

Max Activating Token Index: 557

Text #4

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2003. Min Act: -0.0000

Data Index: 1441321 (Python Code)

Max Activating Token Index: 959

Text #5

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.1800. Min Act: -0.0000

Data Index: 1398263 (Python Code)

Max Activating Token Index: 190

Text #6

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2216. Min Act: -0.0000

Data Index: 1412694 (Python Code)

Max Activating Token Index: 759

Text #7

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.1996. Min Act: -0.0000

Data Index: 1195971 (C4 (Web Text))

Max Activating Token Index: 744

Text #8

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2062. Min Act: -0.0000

Data Index: 1389798 (Python Code)

Max Activating Token Index: 1005

Text #9

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.1873. Min Act: -0.0000

Data Index: 1549559 (Python Code)

Max Activating Token Index: 620

Text #10

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.1993. Min Act: -0.0000

Data Index: 1501411 (Python Code)

Max Activating Token Index: 871

Text #11

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.1759. Min Act: -0.0000

Data Index: 1521089 (Python Code)

Max Activating Token Index: 268

Text #12

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.1813. Min Act: -0.0000

Data Index: 1524684 (Python Code)

Max Activating Token Index: 184

Text #13

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.1880. Min Act: -0.0000

Data Index: 1376119 (Python Code)

Max Activating Token Index: 168

Text #14

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.1850. Min Act: -0.0000

Data Index: 1507177 (Python Code)

Max Activating Token Index: 856

Text #15

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.1896. Min Act: -0.0000

Data Index: 1518244 (Python Code)

Max Activating Token Index: 132

Text #16

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.1682. Min Act: -0.0000

Data Index: 588441 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.1767. Min Act: -0.0000

Data Index: 1304061 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.1620. Min Act: -0.0000

Data Index: 1466237 (Python Code)

Max Activating Token Index: 709

Text #19

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.1683. Min Act: -0.0000

Data Index: 1616622 (Python Code)

Max Activating Token Index: 989