Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1787 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.2220. Min Act: -0.0004

Data Index: 1650794 (Python Code)

Max Activating Token Index: 109

Text #1

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.2182. Min Act: -0.0003

Data Index: 1422391 (Python Code)

Max Activating Token Index: 937

Text #2

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.2010. Min Act: -0.0004

Data Index: 1423075 (Python Code)

Max Activating Token Index: 357

Text #3

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1927. Min Act: -0.0003

Data Index: 1396643 (Python Code)

Max Activating Token Index: 954

Text #4

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.2002. Min Act: -0.0003

Data Index: 1641694 (Python Code)

Max Activating Token Index: 471

Text #5

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1890. Min Act: -0.0003

Data Index: 1522071 (Python Code)

Max Activating Token Index: 623

Text #6

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1845. Min Act: -0.0004

Data Index: 1654117 (Python Code)

Max Activating Token Index: 646

Text #7

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1825. Min Act: -0.0003

Data Index: 1495856 (Python Code)

Max Activating Token Index: 203

Text #8

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1881. Min Act: -0.0003

Data Index: 1623035 (Python Code)

Max Activating Token Index: 942

Text #9

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1873. Min Act: -0.0004

Data Index: 1628097 (Python Code)

Max Activating Token Index: 944

Text #10

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1836. Min Act: -0.0003

Data Index: 1476670 (Python Code)

Max Activating Token Index: 948

Text #11

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1818. Min Act: -0.0003

Data Index: 1413389 (Python Code)

Max Activating Token Index: 128

Text #12

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1823. Min Act: -0.0003

Data Index: 1563996 (Python Code)

Max Activating Token Index: 588

Text #13

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1771. Min Act: -0.0003

Data Index: 1630291 (Python Code)

Max Activating Token Index: 657

Text #14

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1826. Min Act: -0.0003

Data Index: 1367510 (Python Code)

Max Activating Token Index: 225

Text #15

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1763. Min Act: -0.0003

Data Index: 1407372 (Python Code)

Max Activating Token Index: 900

Text #16

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1828. Min Act: -0.0003

Data Index: 1450660 (Python Code)

Max Activating Token Index: 481

Text #17

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1787. Min Act: -0.0003

Data Index: 1620640 (Python Code)

Max Activating Token Index: 719

Text #18

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1767. Min Act: -0.0003

Data Index: 1446701 (Python Code)

Max Activating Token Index: 718

Text #19

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1762. Min Act: -0.0003

Data Index: 1437355 (Python Code)

Max Activating Token Index: 835