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

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

Neuron 220 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.2263. Min Act: -0.0001

Data Index: 1405855 (Python Code)

Max Activating Token Index: 644

Text #1

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.2202. Min Act: -0.0000

Data Index: 1582359 (Python Code)

Max Activating Token Index: 737

Text #2

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1964. Min Act: -0.0001

Data Index: 1509087 (Python Code)

Max Activating Token Index: 44

Text #3

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.2053. Min Act: -0.0001

Data Index: 1363634 (Python Code)

Max Activating Token Index: 566

Text #4

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1910. Min Act: -0.0001

Data Index: 1396569 (Python Code)

Max Activating Token Index: 908

Text #5

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.2003. Min Act: -0.0001

Data Index: 1558474 (Python Code)

Max Activating Token Index: 376

Text #6

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1900. Min Act: -0.0001

Data Index: 1582289 (Python Code)

Max Activating Token Index: 450

Text #7

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1884. Min Act: -0.0001

Data Index: 1368060 (Python Code)

Max Activating Token Index: 991

Text #8

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1829. Min Act: -0.0000

Data Index: 1561822 (Python Code)

Max Activating Token Index: 352

Text #9

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1953. Min Act: -0.0001

Data Index: 1473615 (Python Code)

Max Activating Token Index: 655

Text #10

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1879. Min Act: 0.0000

Data Index: 1540232 (Python Code)

Max Activating Token Index: 101

Text #11

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1846. Min Act: -0.0001

Data Index: 1522273 (Python Code)

Max Activating Token Index: 696

Text #12

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1795. Min Act: -0.0001

Data Index: 1456029 (Python Code)

Max Activating Token Index: 266

Text #13

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1838. Min Act: -0.0001

Data Index: 1405469 (Python Code)

Max Activating Token Index: 568

Text #14

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1775. Min Act: -0.0001

Data Index: 1244014 (C4 (Web Text))

Max Activating Token Index: 250

Text #15

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1771. Min Act: -0.0001

Data Index: 1457114 (Python Code)

Max Activating Token Index: 748

Text #16

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1783. Min Act: -0.0001

Data Index: 1355514 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1710. Min Act: -0.0001

Data Index: 1414337 (Python Code)

Max Activating Token Index: 41

Text #18

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1885. Min Act: -0.0001

Data Index: 1437925 (Python Code)

Max Activating Token Index: 914

Text #19

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1770. Min Act: -0.0001

Data Index: 1362949 (Python Code)

Max Activating Token Index: 911