Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 162 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 9.3076. Min Range: -9.3076

Max Act: 9.2453. Min Act: -0.0000

Data Index: 1531779 (Python Code)

Max Activating Token Index: 935

Text #1

Max Range: 9.3076. Min Range: -9.3076

Max Act: 9.2268. Min Act: -0.0000

Data Index: 1554175 (Python Code)

Max Activating Token Index: 991

Text #2

Max Range: 9.3076. Min Range: -9.3076

Max Act: 9.3076. Min Act: -0.0000

Data Index: 1386205 (Python Code)

Max Activating Token Index: 812

Text #3

Max Range: 9.3076. Min Range: -9.3076

Max Act: 8.8116. Min Act: -0.0000

Data Index: 1453609 (Python Code)

Max Activating Token Index: 956

Text #4

Max Range: 9.3076. Min Range: -9.3076

Max Act: 8.8336. Min Act: -0.0000

Data Index: 1641857 (Python Code)

Max Activating Token Index: 938

Text #5

Max Range: 9.3076. Min Range: -9.3076

Max Act: 8.2365. Min Act: -0.0000

Data Index: 1458080 (Python Code)

Max Activating Token Index: 700

Text #6

Max Range: 9.3076. Min Range: -9.3076

Max Act: 8.7651. Min Act: -0.0000

Data Index: 1584708 (Python Code)

Max Activating Token Index: 703

Text #7

Max Range: 9.3076. Min Range: -9.3076

Max Act: 8.2762. Min Act: -0.0000

Data Index: 1521463 (Python Code)

Max Activating Token Index: 529

Text #8

Max Range: 9.3076. Min Range: -9.3076

Max Act: 8.3672. Min Act: -0.0000

Data Index: 1478819 (Python Code)

Max Activating Token Index: 652

Text #9

Max Range: 9.3076. Min Range: -9.3076

Max Act: 8.9699. Min Act: -0.0000

Data Index: 1446512 (Python Code)

Max Activating Token Index: 682

Text #10

Max Range: 9.3076. Min Range: -9.3076

Max Act: 8.6198. Min Act: -0.0000

Data Index: 1614579 (Python Code)

Max Activating Token Index: 632

Text #11

Max Range: 9.3076. Min Range: -9.3076

Max Act: 8.3345. Min Act: -0.0000

Data Index: 1393973 (Python Code)

Max Activating Token Index: 856

Text #12

Max Range: 9.3076. Min Range: -9.3076

Max Act: 8.5120. Min Act: -0.0000

Data Index: 1420602 (Python Code)

Max Activating Token Index: 951

Text #13

Max Range: 9.3076. Min Range: -9.3076

Max Act: 8.0201. Min Act: -0.0000

Data Index: 1629663 (Python Code)

Max Activating Token Index: 291

Text #14

Max Range: 9.3076. Min Range: -9.3076

Max Act: 8.2838. Min Act: -0.0000

Data Index: 1442894 (Python Code)

Max Activating Token Index: 1002

Text #15

Max Range: 9.3076. Min Range: -9.3076

Max Act: 8.1202. Min Act: -0.0000

Data Index: 1492034 (Python Code)

Max Activating Token Index: 547

Text #16

Max Range: 9.3076. Min Range: -9.3076

Max Act: 7.9805. Min Act: -0.0000

Data Index: 1401014 (Python Code)

Max Activating Token Index: 658

Text #17

Max Range: 9.3076. Min Range: -9.3076

Max Act: 7.7319. Min Act: -0.0000

Data Index: 1626817 (Python Code)

Max Activating Token Index: 933

Text #18

Max Range: 9.3076. Min Range: -9.3076

Max Act: 8.1066. Min Act: -0.0000

Data Index: 1613505 (Python Code)

Max Activating Token Index: 393

Text #19

Max Range: 9.3076. Min Range: -9.3076

Max Act: 7.2213. Min Act: -0.0000

Data Index: 1627496 (Python Code)

Max Activating Token Index: 620