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

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

Neuron 3264 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7076. Min Range: -2.7076

Max Act: 2.7076. Min Act: -0.0000

Data Index: 1421811 (Python Code)

Max Activating Token Index: 40

Text #1

Max Range: 2.7076. Min Range: -2.7076

Max Act: 2.4717. Min Act: -0.0000

Data Index: 1591450 (Python Code)

Max Activating Token Index: 137

Text #2

Max Range: 2.7076. Min Range: -2.7076

Max Act: 2.2331. Min Act: -0.0000

Data Index: 1428277 (Python Code)

Max Activating Token Index: 269

Text #3

Max Range: 2.7076. Min Range: -2.7076

Max Act: 2.2197. Min Act: -0.0000

Data Index: 1625014 (Python Code)

Max Activating Token Index: 634

Text #4

Max Range: 2.7076. Min Range: -2.7076

Max Act: 2.2417. Min Act: -0.0000

Data Index: 1544085 (Python Code)

Max Activating Token Index: 247

Text #5

Max Range: 2.7076. Min Range: -2.7076

Max Act: 2.3423. Min Act: -0.0000

Data Index: 1598194 (Python Code)

Max Activating Token Index: 991

Text #6

Max Range: 2.7076. Min Range: -2.7076

Max Act: 2.3349. Min Act: -0.0000

Data Index: 1565738 (Python Code)

Max Activating Token Index: 892

Text #7

Max Range: 2.7076. Min Range: -2.7076

Max Act: 1.9479. Min Act: -0.0000

Data Index: 1462019 (Python Code)

Max Activating Token Index: 832

Text #8

Max Range: 2.7076. Min Range: -2.7076

Max Act: 2.0809. Min Act: -0.0000

Data Index: 1501882 (Python Code)

Max Activating Token Index: 513

Text #9

Max Range: 2.7076. Min Range: -2.7076

Max Act: 2.0260. Min Act: -0.0000

Data Index: 1490977 (Python Code)

Max Activating Token Index: 113

Text #10

Max Range: 2.7076. Min Range: -2.7076

Max Act: 2.1752. Min Act: -0.0000

Data Index: 1428480 (Python Code)

Max Activating Token Index: 324

Text #11

Max Range: 2.7076. Min Range: -2.7076

Max Act: 2.0146. Min Act: -0.0000

Data Index: 1651021 (Python Code)

Max Activating Token Index: 273

Text #12

Max Range: 2.7076. Min Range: -2.7076

Max Act: 2.0876. Min Act: -0.0000

Data Index: 1639570 (Python Code)

Max Activating Token Index: 65

Text #13

Max Range: 2.7076. Min Range: -2.7076

Max Act: 2.0777. Min Act: -0.0000

Data Index: 1371507 (Python Code)

Max Activating Token Index: 37

Text #14

Max Range: 2.7076. Min Range: -2.7076

Max Act: 2.0742. Min Act: -0.0000

Data Index: 1598307 (Python Code)

Max Activating Token Index: 228

Text #15

Max Range: 2.7076. Min Range: -2.7076

Max Act: 2.0134. Min Act: -0.0000

Data Index: 1613537 (Python Code)

Max Activating Token Index: 915

Text #16

Max Range: 2.7076. Min Range: -2.7076

Max Act: 1.8811. Min Act: -0.0000

Data Index: 1564318 (Python Code)

Max Activating Token Index: 524

Text #17

Max Range: 2.7076. Min Range: -2.7076

Max Act: 1.7888. Min Act: -0.0000

Data Index: 1498427 (Python Code)

Max Activating Token Index: 764

Text #18

Max Range: 2.7076. Min Range: -2.7076

Max Act: 2.0877. Min Act: -0.0000

Data Index: 1628845 (Python Code)

Max Activating Token Index: 852

Text #19

Max Range: 2.7076. Min Range: -2.7076

Max Act: 1.9798. Min Act: -0.0000

Data Index: 1594991 (Python Code)

Max Activating Token Index: 135