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

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

Neuron 91 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: 4.7120. Min Range: -4.7120

Max Act: 4.7120. Min Act: -0.0000

Data Index: 1440745 (Python Code)

Max Activating Token Index: 732

Text #1

Max Range: 4.7120. Min Range: -4.7120

Max Act: 4.3347. Min Act: -0.0000

Data Index: 1502864 (Python Code)

Max Activating Token Index: 6

Text #2

Max Range: 4.7120. Min Range: -4.7120

Max Act: 4.2193. Min Act: -0.0000

Data Index: 1597012 (Python Code)

Max Activating Token Index: 63

Text #3

Max Range: 4.7120. Min Range: -4.7120

Max Act: 4.0324. Min Act: -0.0000

Data Index: 1437686 (Python Code)

Max Activating Token Index: 193

Text #4

Max Range: 4.7120. Min Range: -4.7120

Max Act: 4.1861. Min Act: -0.0000

Data Index: 1627409 (Python Code)

Max Activating Token Index: 725

Text #5

Max Range: 4.7120. Min Range: -4.7120

Max Act: 3.9717. Min Act: -0.0001

Data Index: 1471329 (Python Code)

Max Activating Token Index: 23

Text #6

Max Range: 4.7120. Min Range: -4.7120

Max Act: 3.6266. Min Act: -0.0000

Data Index: 1440176 (Python Code)

Max Activating Token Index: 7

Text #7

Max Range: 4.7120. Min Range: -4.7120

Max Act: 3.5912. Min Act: -0.0000

Data Index: 1568783 (Python Code)

Max Activating Token Index: 184

Text #8

Max Range: 4.7120. Min Range: -4.7120

Max Act: 3.7158. Min Act: -0.0000

Data Index: 1384598 (Python Code)

Max Activating Token Index: 509

Text #9

Max Range: 4.7120. Min Range: -4.7120

Max Act: 3.5362. Min Act: -0.0000

Data Index: 1496514 (Python Code)

Max Activating Token Index: 509

Text #10

Max Range: 4.7120. Min Range: -4.7120

Max Act: 3.6903. Min Act: -0.0000

Data Index: 1380884 (Python Code)

Max Activating Token Index: 8

Text #11

Max Range: 4.7120. Min Range: -4.7120

Max Act: 3.6521. Min Act: -0.0000

Data Index: 1589105 (Python Code)

Max Activating Token Index: 53

Text #12

Max Range: 4.7120. Min Range: -4.7120

Max Act: 3.6529. Min Act: -0.0000

Data Index: 1578135 (Python Code)

Max Activating Token Index: 15

Text #13

Max Range: 4.7120. Min Range: -4.7120

Max Act: 3.7487. Min Act: -0.0000

Data Index: 1622636 (Python Code)

Max Activating Token Index: 78

Text #14

Max Range: 4.7120. Min Range: -4.7120

Max Act: 3.5682. Min Act: -0.0000

Data Index: 1499256 (Python Code)

Max Activating Token Index: 30

Text #15

Max Range: 4.7120. Min Range: -4.7120

Max Act: 3.5393. Min Act: -0.0000

Data Index: 1444109 (Python Code)

Max Activating Token Index: 20

Text #16

Max Range: 4.7120. Min Range: -4.7120

Max Act: 3.3850. Min Act: -0.0000

Data Index: 1649676 (Python Code)

Max Activating Token Index: 3

Text #17

Max Range: 4.7120. Min Range: -4.7120

Max Act: 3.5070. Min Act: -0.0000

Data Index: 1638648 (Python Code)

Max Activating Token Index: 17

Text #18

Max Range: 4.7120. Min Range: -4.7120

Max Act: 3.3739. Min Act: -0.0000

Data Index: 1464912 (Python Code)

Max Activating Token Index: 754

Text #19

Max Range: 4.7120. Min Range: -4.7120

Max Act: 3.4852. Min Act: -0.0000

Data Index: 1436866 (Python Code)

Max Activating Token Index: 59