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

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

Neuron 2533 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: 1.9727. Min Range: -1.9727

Max Act: 1.7606. Min Act: -0.0000

Data Index: 1133857 (C4 (Web Text))

Max Activating Token Index: 765

Text #1

Max Range: 1.9727. Min Range: -1.9727

Max Act: 1.9369. Min Act: -0.0000

Data Index: 915533 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 1.9727. Min Range: -1.9727

Max Act: 1.9727. Min Act: -0.0000

Data Index: 333552 (C4 (Web Text))

Max Activating Token Index: 492

Text #3

Max Range: 1.9727. Min Range: -1.9727

Max Act: 1.8732. Min Act: -0.0000

Data Index: 956119 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 1.9727. Min Range: -1.9727

Max Act: 1.7233. Min Act: -0.0000

Data Index: 1006160 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 1.9727. Min Range: -1.9727

Max Act: 1.8119. Min Act: -0.0000

Data Index: 207938 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 1.9727. Min Range: -1.9727

Max Act: 1.7515. Min Act: -0.0000

Data Index: 33497 (C4 (Web Text))

Max Activating Token Index: 921

Text #7

Max Range: 1.9727. Min Range: -1.9727

Max Act: 1.6310. Min Act: -0.0000

Data Index: 554294 (C4 (Web Text))

Max Activating Token Index: 373

Text #8

Max Range: 1.9727. Min Range: -1.9727

Max Act: 1.6885. Min Act: -0.0000

Data Index: 917803 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 1.9727. Min Range: -1.9727

Max Act: 1.7429. Min Act: -0.0000

Data Index: 758727 (C4 (Web Text))

Max Activating Token Index: 509

Text #10

Max Range: 1.9727. Min Range: -1.9727

Max Act: 1.6194. Min Act: -0.0000

Data Index: 683871 (C4 (Web Text))

Max Activating Token Index: 716

Text #11

Max Range: 1.9727. Min Range: -1.9727

Max Act: 1.5204. Min Act: -0.0000

Data Index: 591270 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 1.9727. Min Range: -1.9727

Max Act: 1.4915. Min Act: -0.0000

Data Index: 1150367 (C4 (Web Text))

Max Activating Token Index: 472

Text #13

Max Range: 1.9727. Min Range: -1.9727

Max Act: 1.5852. Min Act: -0.0000

Data Index: 1147818 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 1.9727. Min Range: -1.9727

Max Act: 1.4669. Min Act: -0.0000

Data Index: 1063887 (C4 (Web Text))

Max Activating Token Index: 294

Text #15

Max Range: 1.9727. Min Range: -1.9727

Max Act: 1.6228. Min Act: -0.0000

Data Index: 832015 (C4 (Web Text))

Max Activating Token Index: 544

Text #16

Max Range: 1.9727. Min Range: -1.9727

Max Act: 1.5313. Min Act: -0.0000

Data Index: 1172617 (C4 (Web Text))

Max Activating Token Index: 862

Text #17

Max Range: 1.9727. Min Range: -1.9727

Max Act: 1.5220. Min Act: -0.0000

Data Index: 370701 (C4 (Web Text))

Max Activating Token Index: 806

Text #18

Max Range: 1.9727. Min Range: -1.9727

Max Act: 1.4164. Min Act: -0.0000

Data Index: 743463 (C4 (Web Text))

Max Activating Token Index: 559

Text #19

Max Range: 1.9727. Min Range: -1.9727

Max Act: 1.4868. Min Act: -0.0000

Data Index: 627573 (C4 (Web Text))

Max Activating Token Index: 21