Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 768 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0302. Min Act: -0.0004

Data Index: 1463718 (Python Code)

Max Activating Token Index: 571

Text #1

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0315. Min Act: -0.0004

Data Index: 909807 (C4 (Web Text))

Max Activating Token Index: 224

Text #2

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0308. Min Act: -0.0004

Data Index: 248759 (C4 (Web Text))

Max Activating Token Index: 934

Text #3

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0293. Min Act: -0.0004

Data Index: 9989 (C4 (Web Text))

Max Activating Token Index: 872

Text #4

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0311. Min Act: -0.0004

Data Index: 435513 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0295. Min Act: -0.0004

Data Index: 1251586 (C4 (Web Text))

Max Activating Token Index: 949

Text #6

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0288. Min Act: -0.0004

Data Index: 1014723 (C4 (Web Text))

Max Activating Token Index: 634

Text #7

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0287. Min Act: -0.0004

Data Index: 1125678 (C4 (Web Text))

Max Activating Token Index: 619

Text #8

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0304. Min Act: -0.0004

Data Index: 507863 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0291. Min Act: -0.0004

Data Index: 13473 (C4 (Web Text))

Max Activating Token Index: 569

Text #10

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0304. Min Act: -0.0004

Data Index: 158919 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0291. Min Act: -0.0004

Data Index: 488995 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0285. Min Act: -0.0004

Data Index: 958228 (C4 (Web Text))

Max Activating Token Index: 1009

Text #13

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0288. Min Act: -0.0004

Data Index: 223810 (C4 (Web Text))

Max Activating Token Index: 738

Text #14

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0245. Min Act: -0.0004

Data Index: 333855 (C4 (Web Text))

Max Activating Token Index: 652

Text #15

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0270. Min Act: -0.0004

Data Index: 1196647 (C4 (Web Text))

Max Activating Token Index: 333

Text #16

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0293. Min Act: -0.0004

Data Index: 22682 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0300. Min Act: -0.0004

Data Index: 88036 (C4 (Web Text))

Max Activating Token Index: 993

Text #18

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0293. Min Act: -0.0004

Data Index: 787879 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0300. Min Act: -0.0004

Data Index: 765315 (C4 (Web Text))

Max Activating Token Index: 260