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

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

Neuron 3307 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2623. Min Range: -1.2623

Max Act: 1.2623. Min Act: -0.0000

Data Index: 1454454 (Python Code)

Max Activating Token Index: 586

Text #1

Max Range: 1.2623. Min Range: -1.2623

Max Act: 1.2009. Min Act: -0.0000

Data Index: 1494227 (Python Code)

Max Activating Token Index: 17

Text #2

Max Range: 1.2623. Min Range: -1.2623

Max Act: 1.0787. Min Act: -0.0000

Data Index: 1581371 (Python Code)

Max Activating Token Index: 143

Text #3

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.9775. Min Act: -0.0000

Data Index: 1460888 (Python Code)

Max Activating Token Index: 36

Text #4

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.9678. Min Act: -0.0000

Data Index: 1480253 (Python Code)

Max Activating Token Index: 65

Text #5

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.9776. Min Act: -0.0000

Data Index: 1631627 (Python Code)

Max Activating Token Index: 124

Text #6

Max Range: 1.2623. Min Range: -1.2623

Max Act: 1.0077. Min Act: -0.0000

Data Index: 1462756 (Python Code)

Max Activating Token Index: 425

Text #7

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.8369. Min Act: -0.0000

Data Index: 1607524 (Python Code)

Max Activating Token Index: 28

Text #8

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.8427. Min Act: -0.0000

Data Index: 1479912 (Python Code)

Max Activating Token Index: 101

Text #9

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.8141. Min Act: -0.0000

Data Index: 1637468 (Python Code)

Max Activating Token Index: 81

Text #10

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.7493. Min Act: -0.0000

Data Index: 1547917 (Python Code)

Max Activating Token Index: 19

Text #11

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.8362. Min Act: -0.0000

Data Index: 1644488 (Python Code)

Max Activating Token Index: 390

Text #12

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.8227. Min Act: -0.0000

Data Index: 1485718 (Python Code)

Max Activating Token Index: 16

Text #13

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.7957. Min Act: -0.0000

Data Index: 1360511 (Python Code)

Max Activating Token Index: 124

Text #14

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.8098. Min Act: -0.0000

Data Index: 1610601 (Python Code)

Max Activating Token Index: 247

Text #15

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.7544. Min Act: -0.0000

Data Index: 1373962 (Python Code)

Max Activating Token Index: 94

Text #16

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.7100. Min Act: -0.0000

Data Index: 1361340 (Python Code)

Max Activating Token Index: 872

Text #17

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.7459. Min Act: -0.0000

Data Index: 1373291 (Python Code)

Max Activating Token Index: 20

Text #18

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.7258. Min Act: -0.0000

Data Index: 1555847 (Python Code)

Max Activating Token Index: 292

Text #19

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.7200. Min Act: -0.0000

Data Index: 1364659 (Python Code)

Max Activating Token Index: 646