Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5530 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.2254. Min Act: -0.0001

Data Index: 1387491 (Python Code)

Max Activating Token Index: 281

Text #1

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1973. Min Act: -0.0001

Data Index: 1557472 (Python Code)

Max Activating Token Index: 33

Text #2

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1960. Min Act: -0.0001

Data Index: 1560167 (Python Code)

Max Activating Token Index: 664

Text #3

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1962. Min Act: -0.0001

Data Index: 1412206 (Python Code)

Max Activating Token Index: 41

Text #4

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1893. Min Act: -0.0001

Data Index: 1556437 (Python Code)

Max Activating Token Index: 898

Text #5

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1899. Min Act: -0.0001

Data Index: 1360410 (Python Code)

Max Activating Token Index: 24

Text #6

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1833. Min Act: -0.0001

Data Index: 1475559 (Python Code)

Max Activating Token Index: 185

Text #7

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1867. Min Act: -0.0001

Data Index: 1383514 (Python Code)

Max Activating Token Index: 17

Text #8

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1808. Min Act: -0.0001

Data Index: 1551392 (Python Code)

Max Activating Token Index: 14

Text #9

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1957. Min Act: -0.0001

Data Index: 1469042 (Python Code)

Max Activating Token Index: 248

Text #10

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1891. Min Act: -0.0001

Data Index: 1447144 (Python Code)

Max Activating Token Index: 660

Text #11

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1814. Min Act: -0.0001

Data Index: 1519001 (Python Code)

Max Activating Token Index: 308

Text #12

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1794. Min Act: -0.0001

Data Index: 1474137 (Python Code)

Max Activating Token Index: 836

Text #13

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1747. Min Act: -0.0001

Data Index: 1502714 (Python Code)

Max Activating Token Index: 141

Text #14

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1741. Min Act: -0.0001

Data Index: 1371625 (Python Code)

Max Activating Token Index: 87

Text #15

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1799. Min Act: -0.0001

Data Index: 1458272 (Python Code)

Max Activating Token Index: 648

Text #16

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1811. Min Act: -0.0001

Data Index: 1406235 (Python Code)

Max Activating Token Index: 770

Text #17

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1746. Min Act: -0.0001

Data Index: 1556156 (Python Code)

Max Activating Token Index: 525

Text #18

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1765. Min Act: -0.0001

Data Index: 1650304 (Python Code)

Max Activating Token Index: 49

Text #19

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1779. Min Act: -0.0001

Data Index: 1520354 (Python Code)

Max Activating Token Index: 15