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

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

Neuron 2673 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3344. Min Range: -1.3344

Max Act: 1.3344. Min Act: -0.0003

Data Index: 1608764 (Python Code)

Max Activating Token Index: 177

Text #1

Max Range: 1.3344. Min Range: -1.3344

Max Act: 1.2158. Min Act: -0.0003

Data Index: 1629142 (Python Code)

Max Activating Token Index: 915

Text #2

Max Range: 1.3344. Min Range: -1.3344

Max Act: 1.1048. Min Act: -0.0003

Data Index: 1437196 (Python Code)

Max Activating Token Index: 790

Text #3

Max Range: 1.3344. Min Range: -1.3344

Max Act: 1.0424. Min Act: -0.0003

Data Index: 1539755 (Python Code)

Max Activating Token Index: 638

Text #4

Max Range: 1.3344. Min Range: -1.3344

Max Act: 1.0720. Min Act: -0.0003

Data Index: 1570271 (Python Code)

Max Activating Token Index: 706

Text #5

Max Range: 1.3344. Min Range: -1.3344

Max Act: 1.1002. Min Act: -0.0003

Data Index: 1573288 (Python Code)

Max Activating Token Index: 904

Text #6

Max Range: 1.3344. Min Range: -1.3344

Max Act: 0.9651. Min Act: -0.0003

Data Index: 1544867 (Python Code)

Max Activating Token Index: 984

Text #7

Max Range: 1.3344. Min Range: -1.3344

Max Act: 1.0584. Min Act: -0.0003

Data Index: 1444851 (Python Code)

Max Activating Token Index: 638

Text #8

Max Range: 1.3344. Min Range: -1.3344

Max Act: 0.9636. Min Act: -0.0003

Data Index: 1613939 (Python Code)

Max Activating Token Index: 556

Text #9

Max Range: 1.3344. Min Range: -1.3344

Max Act: 1.0177. Min Act: -0.0003

Data Index: 1365495 (Python Code)

Max Activating Token Index: 682

Text #10

Max Range: 1.3344. Min Range: -1.3344

Max Act: 1.0206. Min Act: -0.0003

Data Index: 1484739 (Python Code)

Max Activating Token Index: 56

Text #11

Max Range: 1.3344. Min Range: -1.3344

Max Act: 1.0184. Min Act: -0.0003

Data Index: 1554552 (Python Code)

Max Activating Token Index: 330

Text #12

Max Range: 1.3344. Min Range: -1.3344

Max Act: 0.9921. Min Act: -0.0003

Data Index: 1508787 (Python Code)

Max Activating Token Index: 874

Text #13

Max Range: 1.3344. Min Range: -1.3344

Max Act: 0.9774. Min Act: -0.0003

Data Index: 1609021 (Python Code)

Max Activating Token Index: 717

Text #14

Max Range: 1.3344. Min Range: -1.3344

Max Act: 0.9260. Min Act: -0.0003

Data Index: 1577831 (Python Code)

Max Activating Token Index: 678

Text #15

Max Range: 1.3344. Min Range: -1.3344

Max Act: 1.0081. Min Act: -0.0003

Data Index: 1414877 (Python Code)

Max Activating Token Index: 518

Text #16

Max Range: 1.3344. Min Range: -1.3344

Max Act: 1.0466. Min Act: -0.0003

Data Index: 1495920 (Python Code)

Max Activating Token Index: 727

Text #17

Max Range: 1.3344. Min Range: -1.3344

Max Act: 1.0317. Min Act: -0.0003

Data Index: 1543494 (Python Code)

Max Activating Token Index: 737

Text #18

Max Range: 1.3344. Min Range: -1.3344

Max Act: 0.9881. Min Act: -0.0003

Data Index: 1423157 (Python Code)

Max Activating Token Index: 781

Text #19

Max Range: 1.3344. Min Range: -1.3344

Max Act: 0.9565. Min Act: -0.0003

Data Index: 1633620 (Python Code)

Max Activating Token Index: 703