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

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

Neuron 4775 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.6343. Min Act: -0.0000

Data Index: 155407 (C4 (Web Text))

Max Activating Token Index: 621

Text #1

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.6899. Min Act: -0.0000

Data Index: 357177 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.6751. Min Act: -0.0000

Data Index: 961432 (C4 (Web Text))

Max Activating Token Index: 832

Text #3

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.6964. Min Act: -0.0000

Data Index: 1077707 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.7464. Min Act: -0.0000

Data Index: 1161839 (C4 (Web Text))

Max Activating Token Index: 582

Text #5

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.8167. Min Act: -0.0000

Data Index: 676820 (C4 (Web Text))

Max Activating Token Index: 586

Text #6

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.6339. Min Act: -0.0000

Data Index: 977389 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.6283. Min Act: -0.0000

Data Index: 303596 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.5812. Min Act: -0.0000

Data Index: 872217 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.5941. Min Act: -0.0000

Data Index: 756520 (C4 (Web Text))

Max Activating Token Index: 788

Text #10

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.5760. Min Act: -0.0000

Data Index: 1041463 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.5195. Min Act: -0.0000

Data Index: 1213626 (C4 (Web Text))

Max Activating Token Index: 150

Text #12

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.6231. Min Act: -0.0000

Data Index: 121218 (C4 (Web Text))

Max Activating Token Index: 161

Text #13

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.5963. Min Act: -0.0000

Data Index: 221724 (C4 (Web Text))

Max Activating Token Index: 848

Text #14

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.4530. Min Act: -0.0000

Data Index: 73689 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.5241. Min Act: -0.0000

Data Index: 797928 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.4974. Min Act: -0.0000

Data Index: 347335 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.5966. Min Act: -0.0000

Data Index: 497669 (C4 (Web Text))

Max Activating Token Index: 538

Text #18

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.5435. Min Act: -0.0000

Data Index: 974079 (C4 (Web Text))

Max Activating Token Index: 998

Text #19

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.5909. Min Act: -0.0000

Data Index: 1260784 (C4 (Web Text))

Max Activating Token Index: 934