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

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

Neuron 4933 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: 7.0790. Min Range: -7.0790

Max Act: 6.7594. Min Act: -0.0000

Data Index: 711756 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 7.0790. Min Range: -7.0790

Max Act: 7.0790. Min Act: -0.0000

Data Index: 1001657 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 7.0790. Min Range: -7.0790

Max Act: 6.8044. Min Act: -0.0000

Data Index: 37478 (C4 (Web Text))

Max Activating Token Index: 157

Text #3

Max Range: 7.0790. Min Range: -7.0790

Max Act: 6.6989. Min Act: -0.0000

Data Index: 319124 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 7.0790. Min Range: -7.0790

Max Act: 6.1031. Min Act: -0.0000

Data Index: 833406 (C4 (Web Text))

Max Activating Token Index: 127

Text #5

Max Range: 7.0790. Min Range: -7.0790

Max Act: 5.5764. Min Act: -0.0000

Data Index: 13629 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 7.0790. Min Range: -7.0790

Max Act: 5.5584. Min Act: -0.0000

Data Index: 1203323 (C4 (Web Text))

Max Activating Token Index: 955

Text #7

Max Range: 7.0790. Min Range: -7.0790

Max Act: 5.1245. Min Act: -0.0000

Data Index: 708409 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 7.0790. Min Range: -7.0790

Max Act: 5.0920. Min Act: -0.0000

Data Index: 816124 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 7.0790. Min Range: -7.0790

Max Act: 5.4453. Min Act: -0.0000

Data Index: 1189215 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 7.0790. Min Range: -7.0790

Max Act: 4.8697. Min Act: -0.0000

Data Index: 557725 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 7.0790. Min Range: -7.0790

Max Act: 4.8365. Min Act: -0.0000

Data Index: 858990 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 7.0790. Min Range: -7.0790

Max Act: 4.8187. Min Act: -0.0000

Data Index: 996904 (C4 (Web Text))

Max Activating Token Index: 228

Text #13

Max Range: 7.0790. Min Range: -7.0790

Max Act: 4.4972. Min Act: -0.0000

Data Index: 820213 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 7.0790. Min Range: -7.0790

Max Act: 4.8126. Min Act: -0.0000

Data Index: 1149078 (C4 (Web Text))

Max Activating Token Index: 314

Text #15

Max Range: 7.0790. Min Range: -7.0790

Max Act: 4.4222. Min Act: -0.0000

Data Index: 401182 (C4 (Web Text))

Max Activating Token Index: 390

Text #16

Max Range: 7.0790. Min Range: -7.0790

Max Act: 4.4825. Min Act: -0.0000

Data Index: 561626 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 7.0790. Min Range: -7.0790

Max Act: 4.4505. Min Act: -0.0000

Data Index: 685082 (C4 (Web Text))

Max Activating Token Index: 54

Text #18

Max Range: 7.0790. Min Range: -7.0790

Max Act: 4.4890. Min Act: -0.0000

Data Index: 1301460 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 7.0790. Min Range: -7.0790

Max Act: 4.4733. Min Act: -0.0000

Data Index: 685049 (C4 (Web Text))

Max Activating Token Index: 51