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

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

Neuron 3042 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.8074. Min Act: -0.0000

Data Index: 1550498 (Python Code)

Max Activating Token Index: 711

Text #1

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.7470. Min Act: -0.0000

Data Index: 415981 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.6854. Min Act: -0.0000

Data Index: 1583868 (Python Code)

Max Activating Token Index: 825

Text #3

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.7099. Min Act: -0.0000

Data Index: 1383973 (Python Code)

Max Activating Token Index: 80

Text #4

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.6521. Min Act: -0.0000

Data Index: 1396455 (Python Code)

Max Activating Token Index: 850

Text #5

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.6705. Min Act: -0.0000

Data Index: 1641185 (Python Code)

Max Activating Token Index: 503

Text #6

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.6908. Min Act: -0.0000

Data Index: 1569736 (Python Code)

Max Activating Token Index: 992

Text #7

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.6246. Min Act: -0.0000

Data Index: 1632116 (Python Code)

Max Activating Token Index: 804

Text #8

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.6553. Min Act: -0.0000

Data Index: 1020739 (C4 (Web Text))

Max Activating Token Index: 738

Text #9

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.6504. Min Act: -0.0000

Data Index: 573123 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.6018. Min Act: -0.0000

Data Index: 930632 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.6174. Min Act: -0.0000

Data Index: 1556269 (Python Code)

Max Activating Token Index: 593

Text #12

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.6083. Min Act: -0.0001

Data Index: 1514165 (Python Code)

Max Activating Token Index: 76

Text #13

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.6301. Min Act: -0.0000

Data Index: 1424015 (Python Code)

Max Activating Token Index: 552

Text #14

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.5649. Min Act: -0.0000

Data Index: 1499407 (Python Code)

Max Activating Token Index: 943

Text #15

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.5636. Min Act: -0.0000

Data Index: 1455473 (Python Code)

Max Activating Token Index: 754

Text #16

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.5995. Min Act: -0.0000

Data Index: 1601214 (Python Code)

Max Activating Token Index: 850

Text #17

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.5693. Min Act: -0.0000

Data Index: 1427353 (Python Code)

Max Activating Token Index: 304

Text #18

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.5497. Min Act: -0.0000

Data Index: 1123089 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.5218. Min Act: -0.0000

Data Index: 1207854 (C4 (Web Text))

Max Activating Token Index: 1002