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

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

Neuron 5022 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: 1.7572. Min Range: -1.7572

Max Act: 1.6694. Min Act: -0.0000

Data Index: 1435495 (Python Code)

Max Activating Token Index: 739

Text #1

Max Range: 1.7572. Min Range: -1.7572

Max Act: 1.7572. Min Act: -0.0000

Data Index: 1445330 (Python Code)

Max Activating Token Index: 1010

Text #2

Max Range: 1.7572. Min Range: -1.7572

Max Act: 1.7140. Min Act: -0.0000

Data Index: 1598933 (Python Code)

Max Activating Token Index: 865

Text #3

Max Range: 1.7572. Min Range: -1.7572

Max Act: 1.7086. Min Act: -0.0000

Data Index: 1441931 (Python Code)

Max Activating Token Index: 800

Text #4

Max Range: 1.7572. Min Range: -1.7572

Max Act: 1.4253. Min Act: -0.0000

Data Index: 1612737 (Python Code)

Max Activating Token Index: 749

Text #5

Max Range: 1.7572. Min Range: -1.7572

Max Act: 1.5860. Min Act: -0.0000

Data Index: 1561503 (Python Code)

Max Activating Token Index: 560

Text #6

Max Range: 1.7572. Min Range: -1.7572

Max Act: 1.4233. Min Act: -0.0000

Data Index: 1486327 (Python Code)

Max Activating Token Index: 637

Text #7

Max Range: 1.7572. Min Range: -1.7572

Max Act: 1.1781. Min Act: -0.0000

Data Index: 1529546 (Python Code)

Max Activating Token Index: 65

Text #8

Max Range: 1.7572. Min Range: -1.7572

Max Act: 1.1495. Min Act: -0.0000

Data Index: 1464532 (Python Code)

Max Activating Token Index: 569

Text #9

Max Range: 1.7572. Min Range: -1.7572

Max Act: 1.1201. Min Act: -0.0000

Data Index: 1506889 (Python Code)

Max Activating Token Index: 420

Text #10

Max Range: 1.7572. Min Range: -1.7572

Max Act: 1.0866. Min Act: -0.0000

Data Index: 1620926 (Python Code)

Max Activating Token Index: 92

Text #11

Max Range: 1.7572. Min Range: -1.7572

Max Act: 1.1773. Min Act: -0.0000

Data Index: 1372480 (Python Code)

Max Activating Token Index: 454

Text #12

Max Range: 1.7572. Min Range: -1.7572

Max Act: 1.1734. Min Act: -0.0000

Data Index: 1601601 (Python Code)

Max Activating Token Index: 345

Text #13

Max Range: 1.7572. Min Range: -1.7572

Max Act: 0.9447. Min Act: -0.0000

Data Index: 1370720 (Python Code)

Max Activating Token Index: 111

Text #14

Max Range: 1.7572. Min Range: -1.7572

Max Act: 1.0288. Min Act: -0.0000

Data Index: 1572116 (Python Code)

Max Activating Token Index: 300

Text #15

Max Range: 1.7572. Min Range: -1.7572

Max Act: 1.0100. Min Act: -0.0000

Data Index: 1464470 (Python Code)

Max Activating Token Index: 114

Text #16

Max Range: 1.7572. Min Range: -1.7572

Max Act: 1.0489. Min Act: -0.0000

Data Index: 1365962 (Python Code)

Max Activating Token Index: 76

Text #17

Max Range: 1.7572. Min Range: -1.7572

Max Act: 1.0987. Min Act: -0.0000

Data Index: 1505847 (Python Code)

Max Activating Token Index: 86

Text #18

Max Range: 1.7572. Min Range: -1.7572

Max Act: 1.0430. Min Act: -0.0000

Data Index: 1569894 (Python Code)

Max Activating Token Index: 907

Text #19

Max Range: 1.7572. Min Range: -1.7572

Max Act: 1.0672. Min Act: -0.0000

Data Index: 1548488 (Python Code)

Max Activating Token Index: 124