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

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

Neuron 3686 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: 2.1160. Min Range: -2.1160

Max Act: 2.1160. Min Act: -0.0000

Data Index: 1364663 (Python Code)

Max Activating Token Index: 77

Text #1

Max Range: 2.1160. Min Range: -2.1160

Max Act: 2.1070. Min Act: -0.0000

Data Index: 1413211 (Python Code)

Max Activating Token Index: 16

Text #2

Max Range: 2.1160. Min Range: -2.1160

Max Act: 1.9011. Min Act: -0.0000

Data Index: 1576854 (Python Code)

Max Activating Token Index: 53

Text #3

Max Range: 2.1160. Min Range: -2.1160

Max Act: 1.8073. Min Act: -0.0000

Data Index: 1433374 (Python Code)

Max Activating Token Index: 23

Text #4

Max Range: 2.1160. Min Range: -2.1160

Max Act: 1.8257. Min Act: -0.0000

Data Index: 1470143 (Python Code)

Max Activating Token Index: 126

Text #5

Max Range: 2.1160. Min Range: -2.1160

Max Act: 1.8900. Min Act: -0.0000

Data Index: 1587755 (Python Code)

Max Activating Token Index: 35

Text #6

Max Range: 2.1160. Min Range: -2.1160

Max Act: 1.9125. Min Act: -0.0000

Data Index: 1496703 (Python Code)

Max Activating Token Index: 98

Text #7

Max Range: 2.1160. Min Range: -2.1160

Max Act: 1.8713. Min Act: -0.0000

Data Index: 1565797 (Python Code)

Max Activating Token Index: 88

Text #8

Max Range: 2.1160. Min Range: -2.1160

Max Act: 1.8582. Min Act: -0.0000

Data Index: 1622149 (Python Code)

Max Activating Token Index: 13

Text #9

Max Range: 2.1160. Min Range: -2.1160

Max Act: 1.8582. Min Act: -0.0000

Data Index: 1379614 (Python Code)

Max Activating Token Index: 13

Text #10

Max Range: 2.1160. Min Range: -2.1160

Max Act: 1.9527. Min Act: -0.0000

Data Index: 1552231 (Python Code)

Max Activating Token Index: 382

Text #11

Max Range: 2.1160. Min Range: -2.1160

Max Act: 1.8416. Min Act: -0.0000

Data Index: 1426967 (Python Code)

Max Activating Token Index: 138

Text #12

Max Range: 2.1160. Min Range: -2.1160

Max Act: 1.9507. Min Act: -0.0000

Data Index: 1609571 (Python Code)

Max Activating Token Index: 634

Text #13

Max Range: 2.1160. Min Range: -2.1160

Max Act: 1.7788. Min Act: -0.0000

Data Index: 1506996 (Python Code)

Max Activating Token Index: 88

Text #14

Max Range: 2.1160. Min Range: -2.1160

Max Act: 1.9216. Min Act: -0.0000

Data Index: 1587813 (Python Code)

Max Activating Token Index: 47

Text #15

Max Range: 2.1160. Min Range: -2.1160

Max Act: 1.8490. Min Act: -0.0000

Data Index: 1370986 (Python Code)

Max Activating Token Index: 68

Text #16

Max Range: 2.1160. Min Range: -2.1160

Max Act: 1.7969. Min Act: -0.0000

Data Index: 1536009 (Python Code)

Max Activating Token Index: 35

Text #17

Max Range: 2.1160. Min Range: -2.1160

Max Act: 1.7948. Min Act: -0.0000

Data Index: 1564008 (Python Code)

Max Activating Token Index: 100

Text #18

Max Range: 2.1160. Min Range: -2.1160

Max Act: 1.8318. Min Act: -0.0000

Data Index: 1575896 (Python Code)

Max Activating Token Index: 95

Text #19

Max Range: 2.1160. Min Range: -2.1160

Max Act: 1.7274. Min Act: -0.0000

Data Index: 1585966 (Python Code)

Max Activating Token Index: 131