Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3438 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.2542. Min Act: -0.0001

Data Index: 1525447 (Python Code)

Max Activating Token Index: 681

Text #1

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.2119. Min Act: -0.0002

Data Index: 1294531 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.2115. Min Act: -0.0002

Data Index: 1513869 (Python Code)

Max Activating Token Index: 476

Text #3

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1867. Min Act: -0.0001

Data Index: 1540915 (Python Code)

Max Activating Token Index: 511

Text #4

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1683. Min Act: -0.0001

Data Index: 1542957 (Python Code)

Max Activating Token Index: 739

Text #5

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1822. Min Act: -0.0001

Data Index: 1039318 (C4 (Web Text))

Max Activating Token Index: 884

Text #6

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1885. Min Act: -0.0001

Data Index: 1515192 (Python Code)

Max Activating Token Index: 853

Text #7

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1915. Min Act: -0.0001

Data Index: 1406951 (Python Code)

Max Activating Token Index: 573

Text #8

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1891. Min Act: -0.0001

Data Index: 1609363 (Python Code)

Max Activating Token Index: 681

Text #9

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1828. Min Act: -0.0001

Data Index: 1515106 (Python Code)

Max Activating Token Index: 972

Text #10

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1832. Min Act: -0.0001

Data Index: 1651366 (Python Code)

Max Activating Token Index: 852

Text #11

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1815. Min Act: -0.0001

Data Index: 1639535 (Python Code)

Max Activating Token Index: 62

Text #12

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1824. Min Act: -0.0001

Data Index: 1619095 (Python Code)

Max Activating Token Index: 898

Text #13

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1767. Min Act: -0.0001

Data Index: 1650380 (Python Code)

Max Activating Token Index: 307

Text #14

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1722. Min Act: -0.0001

Data Index: 1466178 (Python Code)

Max Activating Token Index: 1020

Text #15

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1764. Min Act: -0.0001

Data Index: 1463392 (Python Code)

Max Activating Token Index: 560

Text #16

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1671. Min Act: -0.0001

Data Index: 1431901 (Python Code)

Max Activating Token Index: 693

Text #17

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1794. Min Act: -0.0001

Data Index: 1419283 (Python Code)

Max Activating Token Index: 104

Text #18

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1704. Min Act: -0.0001

Data Index: 1441895 (Python Code)

Max Activating Token Index: 871

Text #19

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1706. Min Act: -0.0001

Data Index: 1540199 (Python Code)

Max Activating Token Index: 598