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

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

Neuron 843 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8087. Min Range: -1.8087

Max Act: 1.8087. Min Act: -0.0000

Data Index: 1373785 (Python Code)

Max Activating Token Index: 805

Text #1

Max Range: 1.8087. Min Range: -1.8087

Max Act: 1.6893. Min Act: -0.0000

Data Index: 1381453 (Python Code)

Max Activating Token Index: 107

Text #2

Max Range: 1.8087. Min Range: -1.8087

Max Act: 1.5180. Min Act: -0.0000

Data Index: 1433740 (Python Code)

Max Activating Token Index: 942

Text #3

Max Range: 1.8087. Min Range: -1.8087

Max Act: 1.4070. Min Act: -0.0000

Data Index: 1404732 (Python Code)

Max Activating Token Index: 821

Text #4

Max Range: 1.8087. Min Range: -1.8087

Max Act: 1.4846. Min Act: -0.0000

Data Index: 1648515 (Python Code)

Max Activating Token Index: 582

Text #5

Max Range: 1.8087. Min Range: -1.8087

Max Act: 1.4854. Min Act: -0.0000

Data Index: 1383391 (Python Code)

Max Activating Token Index: 250

Text #6

Max Range: 1.8087. Min Range: -1.8087

Max Act: 1.3989. Min Act: -0.0000

Data Index: 1507175 (Python Code)

Max Activating Token Index: 41

Text #7

Max Range: 1.8087. Min Range: -1.8087

Max Act: 1.4469. Min Act: -0.0000

Data Index: 1568071 (Python Code)

Max Activating Token Index: 177

Text #8

Max Range: 1.8087. Min Range: -1.8087

Max Act: 1.2759. Min Act: -0.0000

Data Index: 1426588 (Python Code)

Max Activating Token Index: 89

Text #9

Max Range: 1.8087. Min Range: -1.8087

Max Act: 1.2555. Min Act: -0.0000

Data Index: 1604645 (Python Code)

Max Activating Token Index: 964

Text #10

Max Range: 1.8087. Min Range: -1.8087

Max Act: 1.2349. Min Act: -0.0000

Data Index: 1416569 (Python Code)

Max Activating Token Index: 955

Text #11

Max Range: 1.8087. Min Range: -1.8087

Max Act: 1.2174. Min Act: -0.0000

Data Index: 1488397 (Python Code)

Max Activating Token Index: 686

Text #12

Max Range: 1.8087. Min Range: -1.8087

Max Act: 1.1076. Min Act: -0.0000

Data Index: 1508569 (Python Code)

Max Activating Token Index: 842

Text #13

Max Range: 1.8087. Min Range: -1.8087

Max Act: 1.1410. Min Act: -0.0000

Data Index: 1486752 (Python Code)

Max Activating Token Index: 332

Text #14

Max Range: 1.8087. Min Range: -1.8087

Max Act: 1.1178. Min Act: -0.0000

Data Index: 1438350 (Python Code)

Max Activating Token Index: 924

Text #15

Max Range: 1.8087. Min Range: -1.8087

Max Act: 1.1130. Min Act: -0.0000

Data Index: 1565072 (Python Code)

Max Activating Token Index: 128

Text #16

Max Range: 1.8087. Min Range: -1.8087

Max Act: 1.0342. Min Act: -0.0000

Data Index: 1388250 (Python Code)

Max Activating Token Index: 522

Text #17

Max Range: 1.8087. Min Range: -1.8087

Max Act: 1.0030. Min Act: -0.0000

Data Index: 1364781 (Python Code)

Max Activating Token Index: 847

Text #18

Max Range: 1.8087. Min Range: -1.8087

Max Act: 1.0694. Min Act: -0.0000

Data Index: 1446891 (Python Code)

Max Activating Token Index: 27

Text #19

Max Range: 1.8087. Min Range: -1.8087

Max Act: 1.0692. Min Act: -0.0000

Data Index: 1506629 (Python Code)

Max Activating Token Index: 31