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

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

Neuron 1479 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.9914. Min Range: -1.9914

Max Act: 1.8169. Min Act: -0.0000

Data Index: 612307 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 1.9914. Min Range: -1.9914

Max Act: 1.9914. Min Act: -0.0000

Data Index: 598640 (C4 (Web Text))

Max Activating Token Index: 555

Text #2

Max Range: 1.9914. Min Range: -1.9914

Max Act: 1.7598. Min Act: -0.0000

Data Index: 954930 (C4 (Web Text))

Max Activating Token Index: 8

Text #3

Max Range: 1.9914. Min Range: -1.9914

Max Act: 1.8139. Min Act: -0.0000

Data Index: 1293829 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 1.9914. Min Range: -1.9914

Max Act: 1.7520. Min Act: -0.0000

Data Index: 1116364 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 1.9914. Min Range: -1.9914

Max Act: 1.7157. Min Act: -0.0000

Data Index: 778655 (C4 (Web Text))

Max Activating Token Index: 441

Text #6

Max Range: 1.9914. Min Range: -1.9914

Max Act: 1.6262. Min Act: -0.0000

Data Index: 623072 (C4 (Web Text))

Max Activating Token Index: 685

Text #7

Max Range: 1.9914. Min Range: -1.9914

Max Act: 1.5723. Min Act: -0.0000

Data Index: 1128044 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 1.9914. Min Range: -1.9914

Max Act: 1.3877. Min Act: -0.0000

Data Index: 962344 (C4 (Web Text))

Max Activating Token Index: 277

Text #9

Max Range: 1.9914. Min Range: -1.9914

Max Act: 1.5234. Min Act: -0.0000

Data Index: 749127 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 1.9914. Min Range: -1.9914

Max Act: 1.4816. Min Act: -0.0000

Data Index: 1101330 (C4 (Web Text))

Max Activating Token Index: 387

Text #11

Max Range: 1.9914. Min Range: -1.9914

Max Act: 1.7014. Min Act: -0.0000

Data Index: 710652 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 1.9914. Min Range: -1.9914

Max Act: 1.5052. Min Act: -0.0000

Data Index: 336266 (C4 (Web Text))

Max Activating Token Index: 412

Text #13

Max Range: 1.9914. Min Range: -1.9914

Max Act: 1.4335. Min Act: -0.0000

Data Index: 981658 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 1.9914. Min Range: -1.9914

Max Act: 1.5754. Min Act: -0.0000

Data Index: 1420243 (Python Code)

Max Activating Token Index: 35

Text #15

Max Range: 1.9914. Min Range: -1.9914

Max Act: 1.6129. Min Act: -0.0000

Data Index: 1090529 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 1.9914. Min Range: -1.9914

Max Act: 1.4859. Min Act: -0.0000

Data Index: 617126 (C4 (Web Text))

Max Activating Token Index: 907

Text #17

Max Range: 1.9914. Min Range: -1.9914

Max Act: 1.4455. Min Act: -0.0000

Data Index: 314277 (C4 (Web Text))

Max Activating Token Index: 861

Text #18

Max Range: 1.9914. Min Range: -1.9914

Max Act: 1.4213. Min Act: -0.0000

Data Index: 79965 (C4 (Web Text))

Max Activating Token Index: 457

Text #19

Max Range: 1.9914. Min Range: -1.9914

Max Act: 1.4636. Min Act: -0.0000

Data Index: 936599 (C4 (Web Text))

Max Activating Token Index: 769