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

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

Neuron 1079 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: 0.8141. Min Range: -0.8141

Max Act: 0.8141. Min Act: -0.0000

Data Index: 1466474 (Python Code)

Max Activating Token Index: 955

Text #1

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.7995. Min Act: -0.0000

Data Index: 1451379 (Python Code)

Max Activating Token Index: 954

Text #2

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.7742. Min Act: -0.0000

Data Index: 1578548 (Python Code)

Max Activating Token Index: 924

Text #3

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.7221. Min Act: -0.0001

Data Index: 1545091 (Python Code)

Max Activating Token Index: 373

Text #4

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.6941. Min Act: -0.0000

Data Index: 1622030 (Python Code)

Max Activating Token Index: 598

Text #5

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.6727. Min Act: -0.0001

Data Index: 1552810 (Python Code)

Max Activating Token Index: 920

Text #6

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.7431. Min Act: -0.0000

Data Index: 1512463 (Python Code)

Max Activating Token Index: 289

Text #7

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.6634. Min Act: -0.0000

Data Index: 1478066 (Python Code)

Max Activating Token Index: 883

Text #8

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.7284. Min Act: -0.0000

Data Index: 1538751 (Python Code)

Max Activating Token Index: 261

Text #9

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.6618. Min Act: -0.0000

Data Index: 1607938 (Python Code)

Max Activating Token Index: 391

Text #10

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.6759. Min Act: -0.0000

Data Index: 1616334 (Python Code)

Max Activating Token Index: 200

Text #11

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.6589. Min Act: -0.0000

Data Index: 1624166 (Python Code)

Max Activating Token Index: 740

Text #12

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.6503. Min Act: -0.0000

Data Index: 1375386 (Python Code)

Max Activating Token Index: 5

Text #13

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.6968. Min Act: -0.0000

Data Index: 1443303 (Python Code)

Max Activating Token Index: 767

Text #14

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.5508. Min Act: -0.0000

Data Index: 1581713 (Python Code)

Max Activating Token Index: 711

Text #15

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.6984. Min Act: -0.0000

Data Index: 1586801 (Python Code)

Max Activating Token Index: 216

Text #16

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.6689. Min Act: -0.0000

Data Index: 1521697 (Python Code)

Max Activating Token Index: 564

Text #17

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.7177. Min Act: -0.0000

Data Index: 1462490 (Python Code)

Max Activating Token Index: 974

Text #18

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.6864. Min Act: -0.0000

Data Index: 1619853 (Python Code)

Max Activating Token Index: 1019

Text #19

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.6021. Min Act: -0.0000

Data Index: 1491746 (Python Code)

Max Activating Token Index: 481