Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1301 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7447. Min Range: -0.7447

Max Act: 0.7447. Min Act: -0.0000

Data Index: 1348016 (The Pile)

Max Activating Token Index: 298

Text #1

Max Range: 0.7447. Min Range: -0.7447

Max Act: 0.7166. Min Act: -0.0000

Data Index: 552707 (The Pile)

Max Activating Token Index: 799

Text #2

Max Range: 0.7447. Min Range: -0.7447

Max Act: 0.7290. Min Act: -0.0000

Data Index: 1016495 (The Pile)

Max Activating Token Index: 393

Text #3

Max Range: 0.7447. Min Range: -0.7447

Max Act: 0.6901. Min Act: -0.0000

Data Index: 1525235 (The Pile)

Max Activating Token Index: 899

Text #4

Max Range: 0.7447. Min Range: -0.7447

Max Act: 0.6783. Min Act: -0.0000

Data Index: 1537729 (The Pile)

Max Activating Token Index: 798

Text #5

Max Range: 0.7447. Min Range: -0.7447

Max Act: 0.6595. Min Act: -0.0000

Data Index: 1727978 (The Pile)

Max Activating Token Index: 374

Text #6

Max Range: 0.7447. Min Range: -0.7447

Max Act: 0.6401. Min Act: -0.0000

Data Index: 600289 (The Pile)

Max Activating Token Index: 932

Text #7

Max Range: 0.7447. Min Range: -0.7447

Max Act: 0.6476. Min Act: -0.0000

Data Index: 202787 (The Pile)

Max Activating Token Index: 998

Text #8

Max Range: 0.7447. Min Range: -0.7447

Max Act: 0.6438. Min Act: -0.0000

Data Index: 1539810 (The Pile)

Max Activating Token Index: 344

Text #9

Max Range: 0.7447. Min Range: -0.7447

Max Act: 0.6047. Min Act: -0.0000

Data Index: 1827925 (The Pile)

Max Activating Token Index: 263

Text #10

Max Range: 0.7447. Min Range: -0.7447

Max Act: 0.6133. Min Act: -0.0000

Data Index: 232298 (The Pile)

Max Activating Token Index: 777

Text #11

Max Range: 0.7447. Min Range: -0.7447

Max Act: 0.6518. Min Act: -0.0000

Data Index: 193907 (The Pile)

Max Activating Token Index: 674

Text #12

Max Range: 0.7447. Min Range: -0.7447

Max Act: 0.5874. Min Act: -0.0000

Data Index: 1808749 (The Pile)

Max Activating Token Index: 522

Text #13

Max Range: 0.7447. Min Range: -0.7447

Max Act: 0.5616. Min Act: -0.0000

Data Index: 1375404 (The Pile)

Max Activating Token Index: 890

Text #14

Max Range: 0.7447. Min Range: -0.7447

Max Act: 0.5822. Min Act: -0.0000

Data Index: 1527659 (The Pile)

Max Activating Token Index: 84

Text #15

Max Range: 0.7447. Min Range: -0.7447

Max Act: 0.5947. Min Act: -0.0000

Data Index: 129078 (The Pile)

Max Activating Token Index: 207

Text #16

Max Range: 0.7447. Min Range: -0.7447

Max Act: 0.5914. Min Act: -0.0000

Data Index: 239299 (The Pile)

Max Activating Token Index: 30

Text #17

Max Range: 0.7447. Min Range: -0.7447

Max Act: 0.5897. Min Act: -0.0000

Data Index: 569221 (The Pile)

Max Activating Token Index: 250

Text #18

Max Range: 0.7447. Min Range: -0.7447

Max Act: 0.5690. Min Act: -0.0000

Data Index: 1580409 (The Pile)

Max Activating Token Index: 398

Text #19

Max Range: 0.7447. Min Range: -0.7447

Max Act: 0.5637. Min Act: -0.0000

Data Index: 684597 (The Pile)

Max Activating Token Index: 954