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

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

Neuron 4505 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8357. Min Range: -0.8357

Max Act: 0.7739. Min Act: -0.0000

Data Index: 1640867 (Python Code)

Max Activating Token Index: 506

Text #1

Max Range: 0.8357. Min Range: -0.8357

Max Act: 0.7752. Min Act: -0.0000

Data Index: 1590036 (Python Code)

Max Activating Token Index: 517

Text #2

Max Range: 0.8357. Min Range: -0.8357

Max Act: 0.8357. Min Act: -0.0000

Data Index: 1632290 (Python Code)

Max Activating Token Index: 1014

Text #3

Max Range: 0.8357. Min Range: -0.8357

Max Act: 0.7081. Min Act: -0.0000

Data Index: 1392499 (Python Code)

Max Activating Token Index: 832

Text #4

Max Range: 0.8357. Min Range: -0.8357

Max Act: 0.7210. Min Act: -0.0000

Data Index: 1618080 (Python Code)

Max Activating Token Index: 161

Text #5

Max Range: 0.8357. Min Range: -0.8357

Max Act: 0.7185. Min Act: -0.0000

Data Index: 1585066 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.8357. Min Range: -0.8357

Max Act: 0.6844. Min Act: -0.0000

Data Index: 1641856 (Python Code)

Max Activating Token Index: 995

Text #7

Max Range: 0.8357. Min Range: -0.8357

Max Act: 0.6615. Min Act: -0.0000

Data Index: 1411784 (Python Code)

Max Activating Token Index: 689

Text #8

Max Range: 0.8357. Min Range: -0.8357

Max Act: 0.6505. Min Act: -0.0000

Data Index: 1498030 (Python Code)

Max Activating Token Index: 191

Text #9

Max Range: 0.8357. Min Range: -0.8357

Max Act: 0.6863. Min Act: -0.0000

Data Index: 1568037 (Python Code)

Max Activating Token Index: 871

Text #10

Max Range: 0.8357. Min Range: -0.8357

Max Act: 0.6072. Min Act: -0.0000

Data Index: 1495915 (Python Code)

Max Activating Token Index: 307

Text #11

Max Range: 0.8357. Min Range: -0.8357

Max Act: 0.5972. Min Act: -0.0000

Data Index: 1445604 (Python Code)

Max Activating Token Index: 769

Text #12

Max Range: 0.8357. Min Range: -0.8357

Max Act: 0.5880. Min Act: -0.0000

Data Index: 1496014 (Python Code)

Max Activating Token Index: 922

Text #13

Max Range: 0.8357. Min Range: -0.8357

Max Act: 0.6079. Min Act: -0.0000

Data Index: 1607715 (Python Code)

Max Activating Token Index: 90

Text #14

Max Range: 0.8357. Min Range: -0.8357

Max Act: 0.6123. Min Act: -0.0000

Data Index: 1643052 (Python Code)

Max Activating Token Index: 568

Text #15

Max Range: 0.8357. Min Range: -0.8357

Max Act: 0.5981. Min Act: -0.0000

Data Index: 1498226 (Python Code)

Max Activating Token Index: 102

Text #16

Max Range: 0.8357. Min Range: -0.8357

Max Act: 0.5985. Min Act: -0.0000

Data Index: 1506961 (Python Code)

Max Activating Token Index: 160

Text #17

Max Range: 0.8357. Min Range: -0.8357

Max Act: 0.5566. Min Act: -0.0000

Data Index: 1633425 (Python Code)

Max Activating Token Index: 839

Text #18

Max Range: 0.8357. Min Range: -0.8357

Max Act: 0.5863. Min Act: -0.0000

Data Index: 1636472 (Python Code)

Max Activating Token Index: 799

Text #19

Max Range: 0.8357. Min Range: -0.8357

Max Act: 0.6149. Min Act: -0.0000

Data Index: 1377178 (Python Code)

Max Activating Token Index: 757