Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4098 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8915. Min Range: -1.8915

Max Act: 1.8278. Min Act: -0.0000

Data Index: 1419136 (Python Code)

Max Activating Token Index: 15

Text #1

Max Range: 1.8915. Min Range: -1.8915

Max Act: 1.7988. Min Act: -0.0000

Data Index: 1419166 (Python Code)

Max Activating Token Index: 512

Text #2

Max Range: 1.8915. Min Range: -1.8915

Max Act: 1.6812. Min Act: -0.0000

Data Index: 1408514 (Python Code)

Max Activating Token Index: 157

Text #3

Max Range: 1.8915. Min Range: -1.8915

Max Act: 1.8915. Min Act: 0.0000

Data Index: 1656281 (Python Code)

Max Activating Token Index: 146

Text #4

Max Range: 1.8915. Min Range: -1.8915

Max Act: 1.8103. Min Act: -0.0000

Data Index: 1386721 (Python Code)

Max Activating Token Index: 964

Text #5

Max Range: 1.8915. Min Range: -1.8915

Max Act: 1.6224. Min Act: -0.0000

Data Index: 1612307 (Python Code)

Max Activating Token Index: 215

Text #6

Max Range: 1.8915. Min Range: -1.8915

Max Act: 1.6143. Min Act: -0.0000

Data Index: 1597269 (Python Code)

Max Activating Token Index: 476

Text #7

Max Range: 1.8915. Min Range: -1.8915

Max Act: 1.5878. Min Act: -0.0000

Data Index: 1407566 (Python Code)

Max Activating Token Index: 479

Text #8

Max Range: 1.8915. Min Range: -1.8915

Max Act: 1.5895. Min Act: -0.0000

Data Index: 1503709 (Python Code)

Max Activating Token Index: 892

Text #9

Max Range: 1.8915. Min Range: -1.8915

Max Act: 1.5603. Min Act: -0.0000

Data Index: 1523182 (Python Code)

Max Activating Token Index: 43

Text #10

Max Range: 1.8915. Min Range: -1.8915

Max Act: 1.4785. Min Act: -0.0000

Data Index: 1377915 (Python Code)

Max Activating Token Index: 769

Text #11

Max Range: 1.8915. Min Range: -1.8915

Max Act: 1.5287. Min Act: -0.0000

Data Index: 1404707 (Python Code)

Max Activating Token Index: 84

Text #12

Max Range: 1.8915. Min Range: -1.8915

Max Act: 1.4104. Min Act: -0.0000

Data Index: 1589998 (Python Code)

Max Activating Token Index: 110

Text #13

Max Range: 1.8915. Min Range: -1.8915

Max Act: 1.3982. Min Act: -0.0000

Data Index: 1527469 (Python Code)

Max Activating Token Index: 22

Text #14

Max Range: 1.8915. Min Range: -1.8915

Max Act: 1.3556. Min Act: -0.0000

Data Index: 1653960 (Python Code)

Max Activating Token Index: 142

Text #15

Max Range: 1.8915. Min Range: -1.8915

Max Act: 1.4277. Min Act: -0.0000

Data Index: 1360601 (Python Code)

Max Activating Token Index: 254

Text #16

Max Range: 1.8915. Min Range: -1.8915

Max Act: 1.4122. Min Act: -0.0000

Data Index: 1597121 (Python Code)

Max Activating Token Index: 33

Text #17

Max Range: 1.8915. Min Range: -1.8915

Max Act: 1.4046. Min Act: -0.0000

Data Index: 1643438 (Python Code)

Max Activating Token Index: 100

Text #18

Max Range: 1.8915. Min Range: -1.8915

Max Act: 1.4103. Min Act: -0.0000

Data Index: 1614281 (Python Code)

Max Activating Token Index: 369

Text #19

Max Range: 1.8915. Min Range: -1.8915

Max Act: 1.2508. Min Act: -0.0000

Data Index: 1646198 (Python Code)

Max Activating Token Index: 224