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

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

Neuron 1791 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2197. Min Range: -1.2197

Max Act: 1.2197. Min Act: -0.0000

Data Index: 554607 (C4 (Web Text))

Max Activating Token Index: 571

Text #1

Max Range: 1.2197. Min Range: -1.2197

Max Act: 1.1350. Min Act: -0.0000

Data Index: 317362 (C4 (Web Text))

Max Activating Token Index: 974

Text #2

Max Range: 1.2197. Min Range: -1.2197

Max Act: 1.0503. Min Act: -0.0000

Data Index: 848918 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 1.2197. Min Range: -1.2197

Max Act: 1.0387. Min Act: -0.0000

Data Index: 1017207 (C4 (Web Text))

Max Activating Token Index: 930

Text #4

Max Range: 1.2197. Min Range: -1.2197

Max Act: 0.9971. Min Act: -0.0000

Data Index: 434154 (C4 (Web Text))

Max Activating Token Index: 543

Text #5

Max Range: 1.2197. Min Range: -1.2197

Max Act: 1.0117. Min Act: -0.0000

Data Index: 492970 (C4 (Web Text))

Max Activating Token Index: 607

Text #6

Max Range: 1.2197. Min Range: -1.2197

Max Act: 0.9780. Min Act: -0.0000

Data Index: 465700 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 1.2197. Min Range: -1.2197

Max Act: 1.0342. Min Act: -0.0000

Data Index: 868774 (C4 (Web Text))

Max Activating Token Index: 594

Text #8

Max Range: 1.2197. Min Range: -1.2197

Max Act: 0.9806. Min Act: -0.0000

Data Index: 934594 (C4 (Web Text))

Max Activating Token Index: 702

Text #9

Max Range: 1.2197. Min Range: -1.2197

Max Act: 0.9692. Min Act: -0.0000

Data Index: 656955 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 1.2197. Min Range: -1.2197

Max Act: 0.9616. Min Act: -0.0000

Data Index: 349307 (C4 (Web Text))

Max Activating Token Index: 539

Text #11

Max Range: 1.2197. Min Range: -1.2197

Max Act: 1.0203. Min Act: -0.0000

Data Index: 1011596 (C4 (Web Text))

Max Activating Token Index: 352

Text #12

Max Range: 1.2197. Min Range: -1.2197

Max Act: 0.9356. Min Act: -0.0000

Data Index: 673830 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 1.2197. Min Range: -1.2197

Max Act: 0.9564. Min Act: -0.0000

Data Index: 749502 (C4 (Web Text))

Max Activating Token Index: 1018

Text #14

Max Range: 1.2197. Min Range: -1.2197

Max Act: 0.9444. Min Act: -0.0000

Data Index: 104279 (C4 (Web Text))

Max Activating Token Index: 508

Text #15

Max Range: 1.2197. Min Range: -1.2197

Max Act: 0.9216. Min Act: -0.0000

Data Index: 738770 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 1.2197. Min Range: -1.2197

Max Act: 0.8915. Min Act: -0.0000

Data Index: 1021291 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 1.2197. Min Range: -1.2197

Max Act: 0.9452. Min Act: -0.0000

Data Index: 91057 (C4 (Web Text))

Max Activating Token Index: 450

Text #18

Max Range: 1.2197. Min Range: -1.2197

Max Act: 0.9978. Min Act: -0.0000

Data Index: 214060 (C4 (Web Text))

Max Activating Token Index: 458

Text #19

Max Range: 1.2197. Min Range: -1.2197

Max Act: 0.9166. Min Act: -0.0000

Data Index: 1316465 (C4 (Web Text))

Max Activating Token Index: 847