Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 661 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1631. Min Act: -0.0004

Data Index: 1556427 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1314. Min Act: -0.0004

Data Index: 1430186 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1351. Min Act: -0.0004

Data Index: 1362912 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1239. Min Act: -0.0004

Data Index: 1524834 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1050. Min Act: -0.0004

Data Index: 1433209 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1120. Min Act: -0.0004

Data Index: 1485449 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.0902. Min Act: -0.0004

Data Index: 1655808 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1075. Min Act: -0.0004

Data Index: 1634382 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.0968. Min Act: -0.0004

Data Index: 1545885 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.0991. Min Act: -0.0004

Data Index: 1546735 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.0785. Min Act: -0.0004

Data Index: 1456798 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.0979. Min Act: -0.0004

Data Index: 1375938 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.0781. Min Act: -0.0004

Data Index: 1473052 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.0924. Min Act: -0.0004

Data Index: 1449708 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.0914. Min Act: -0.0004

Data Index: 1400915 (Python Code)

Max Activating Token Index: 261

Text #15

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.0850. Min Act: -0.0004

Data Index: 1457715 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.0872. Min Act: -0.0004

Data Index: 1484826 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.0789. Min Act: -0.0004

Data Index: 1566916 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.0877. Min Act: -0.0004

Data Index: 1476011 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.0774. Min Act: -0.0004

Data Index: 1508159 (Python Code)

Max Activating Token Index: 844