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

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

Neuron 2388 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.2589. Min Act: -0.0000

Data Index: 1403458 (Python Code)

Max Activating Token Index: 417

Text #1

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.2559. Min Act: -0.0000

Data Index: 1495716 (Python Code)

Max Activating Token Index: 444

Text #2

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.2270. Min Act: -0.0000

Data Index: 1601995 (Python Code)

Max Activating Token Index: 814

Text #3

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.2177. Min Act: -0.0000

Data Index: 1378243 (Python Code)

Max Activating Token Index: 739

Text #4

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1969. Min Act: -0.0000

Data Index: 1494392 (Python Code)

Max Activating Token Index: 629

Text #5

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1870. Min Act: -0.0000

Data Index: 1413389 (Python Code)

Max Activating Token Index: 144

Text #6

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1902. Min Act: -0.0000

Data Index: 1458738 (Python Code)

Max Activating Token Index: 548

Text #7

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1783. Min Act: -0.0000

Data Index: 1506821 (Python Code)

Max Activating Token Index: 585

Text #8

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1905. Min Act: -0.0000

Data Index: 1549228 (Python Code)

Max Activating Token Index: 246

Text #9

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1715. Min Act: -0.0000

Data Index: 484611 (C4 (Web Text))

Max Activating Token Index: 553

Text #10

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1723. Min Act: -0.0000

Data Index: 1420973 (Python Code)

Max Activating Token Index: 336

Text #11

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1721. Min Act: -0.0000

Data Index: 1581864 (Python Code)

Max Activating Token Index: 445

Text #12

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1811. Min Act: -0.0000

Data Index: 1375444 (Python Code)

Max Activating Token Index: 711

Text #13

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1704. Min Act: -0.0000

Data Index: 1387552 (Python Code)

Max Activating Token Index: 712

Text #14

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1724. Min Act: -0.0000

Data Index: 1388822 (Python Code)

Max Activating Token Index: 270

Text #15

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1650. Min Act: -0.0000

Data Index: 1517392 (Python Code)

Max Activating Token Index: 205

Text #16

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1606. Min Act: -0.0000

Data Index: 1540937 (Python Code)

Max Activating Token Index: 47

Text #17

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1641. Min Act: -0.0000

Data Index: 1516245 (Python Code)

Max Activating Token Index: 935

Text #18

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1575. Min Act: -0.0000

Data Index: 1620065 (Python Code)

Max Activating Token Index: 560

Text #19

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1477. Min Act: -0.0000

Data Index: 1087664 (C4 (Web Text))

Max Activating Token Index: 819