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

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

Neuron 3713 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9704. Min Range: -3.9704

Max Act: 3.9704. Min Act: -0.0000

Data Index: 440446 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 3.9704. Min Range: -3.9704

Max Act: 3.4762. Min Act: -0.0000

Data Index: 1316111 (C4 (Web Text))

Max Activating Token Index: 814

Text #2

Max Range: 3.9704. Min Range: -3.9704

Max Act: 3.2178. Min Act: -0.0000

Data Index: 51677 (C4 (Web Text))

Max Activating Token Index: 408

Text #3

Max Range: 3.9704. Min Range: -3.9704

Max Act: 3.0342. Min Act: -0.0000

Data Index: 315436 (C4 (Web Text))

Max Activating Token Index: 649

Text #4

Max Range: 3.9704. Min Range: -3.9704

Max Act: 3.0717. Min Act: -0.0000

Data Index: 907672 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 3.9704. Min Range: -3.9704

Max Act: 2.9498. Min Act: -0.0000

Data Index: 206011 (C4 (Web Text))

Max Activating Token Index: 715

Text #6

Max Range: 3.9704. Min Range: -3.9704

Max Act: 3.0298. Min Act: -0.0000

Data Index: 1343899 (C4 (Web Text))

Max Activating Token Index: 1000

Text #7

Max Range: 3.9704. Min Range: -3.9704

Max Act: 2.9115. Min Act: -0.0000

Data Index: 728839 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 3.9704. Min Range: -3.9704

Max Act: 3.0129. Min Act: -0.0000

Data Index: 925047 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 3.9704. Min Range: -3.9704

Max Act: 2.8101. Min Act: -0.0000

Data Index: 426096 (C4 (Web Text))

Max Activating Token Index: 427

Text #10

Max Range: 3.9704. Min Range: -3.9704

Max Act: 2.6223. Min Act: -0.0000

Data Index: 769830 (C4 (Web Text))

Max Activating Token Index: 282

Text #11

Max Range: 3.9704. Min Range: -3.9704

Max Act: 2.7371. Min Act: -0.0000

Data Index: 367546 (C4 (Web Text))

Max Activating Token Index: 456

Text #12

Max Range: 3.9704. Min Range: -3.9704

Max Act: 2.6014. Min Act: -0.0000

Data Index: 608964 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 3.9704. Min Range: -3.9704

Max Act: 2.6941. Min Act: -0.0000

Data Index: 820349 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 3.9704. Min Range: -3.9704

Max Act: 2.6844. Min Act: -0.0000

Data Index: 302847 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 3.9704. Min Range: -3.9704

Max Act: 2.6997. Min Act: -0.0000

Data Index: 739702 (C4 (Web Text))

Max Activating Token Index: 633

Text #16

Max Range: 3.9704. Min Range: -3.9704

Max Act: 2.5368. Min Act: -0.0001

Data Index: 795462 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 3.9704. Min Range: -3.9704

Max Act: 2.6602. Min Act: -0.0000

Data Index: 829863 (C4 (Web Text))

Max Activating Token Index: 611

Text #18

Max Range: 3.9704. Min Range: -3.9704

Max Act: 2.6134. Min Act: -0.0000

Data Index: 490319 (C4 (Web Text))

Max Activating Token Index: 855

Text #19

Max Range: 3.9704. Min Range: -3.9704

Max Act: 2.4685. Min Act: -0.0000

Data Index: 468869 (C4 (Web Text))

Max Activating Token Index: 534