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

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

Neuron 3623 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: 0.7977. Min Range: -0.7977

Max Act: 0.7977. Min Act: 0.0001

Data Index: 1596040 (Python Code)

Max Activating Token Index: 95

Text #1

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.7602. Min Act: 0.0001

Data Index: 1617723 (Python Code)

Max Activating Token Index: 305

Text #2

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.7224. Min Act: -0.0000

Data Index: 1423488 (Python Code)

Max Activating Token Index: 733

Text #3

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.7370. Min Act: -0.0000

Data Index: 1520302 (Python Code)

Max Activating Token Index: 595

Text #4

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.7171. Min Act: 0.0001

Data Index: 1512439 (Python Code)

Max Activating Token Index: 130

Text #5

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.7136. Min Act: -0.0000

Data Index: 1375959 (Python Code)

Max Activating Token Index: 470

Text #6

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.7263. Min Act: -0.0000

Data Index: 228614 (C4 (Web Text))

Max Activating Token Index: 631

Text #7

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.7076. Min Act: -0.0000

Data Index: 1410444 (Python Code)

Max Activating Token Index: 489

Text #8

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.6327. Min Act: 0.0001

Data Index: 1465418 (Python Code)

Max Activating Token Index: 623

Text #9

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.6338. Min Act: 0.0001

Data Index: 1370816 (Python Code)

Max Activating Token Index: 55

Text #10

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.6067. Min Act: 0.0000

Data Index: 1599961 (Python Code)

Max Activating Token Index: 433

Text #11

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.6102. Min Act: -0.0000

Data Index: 1438766 (Python Code)

Max Activating Token Index: 227

Text #12

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.5675. Min Act: 0.0000

Data Index: 1442203 (Python Code)

Max Activating Token Index: 36

Text #13

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.5539. Min Act: 0.0001

Data Index: 1648901 (Python Code)

Max Activating Token Index: 527

Text #14

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.5551. Min Act: 0.0001

Data Index: 1613578 (Python Code)

Max Activating Token Index: 681

Text #15

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.5557. Min Act: 0.0001

Data Index: 1503490 (Python Code)

Max Activating Token Index: 59

Text #16

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.5425. Min Act: 0.0001

Data Index: 1577957 (Python Code)

Max Activating Token Index: 125

Text #17

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.5494. Min Act: 0.0000

Data Index: 1506468 (Python Code)

Max Activating Token Index: 503

Text #18

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.5274. Min Act: 0.0001

Data Index: 1431127 (Python Code)

Max Activating Token Index: 925

Text #19

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.5570. Min Act: 0.0001

Data Index: 1634284 (Python Code)

Max Activating Token Index: 150