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

Dataset: The Pile

Neuron 1674 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3269. Min Range: -1.3269

Max Act: 1.3269. Min Act: -0.0000

Data Index: 966819 (The Pile)

Max Activating Token Index: 382

Text #1

Max Range: 1.3269. Min Range: -1.3269

Max Act: 1.1530. Min Act: -0.0000

Data Index: 1988960 (The Pile)

Max Activating Token Index: 708

Text #2

Max Range: 1.3269. Min Range: -1.3269

Max Act: 1.1747. Min Act: -0.0000

Data Index: 442876 (The Pile)

Max Activating Token Index: 323

Text #3

Max Range: 1.3269. Min Range: -1.3269

Max Act: 1.2377. Min Act: -0.0000

Data Index: 221736 (The Pile)

Max Activating Token Index: 595

Text #4

Max Range: 1.3269. Min Range: -1.3269

Max Act: 1.1206. Min Act: -0.0000

Data Index: 663713 (The Pile)

Max Activating Token Index: 426

Text #5

Max Range: 1.3269. Min Range: -1.3269

Max Act: 1.1630. Min Act: -0.0000

Data Index: 275180 (The Pile)

Max Activating Token Index: 493

Text #6

Max Range: 1.3269. Min Range: -1.3269

Max Act: 1.1740. Min Act: -0.0000

Data Index: 638543 (The Pile)

Max Activating Token Index: 499

Text #7

Max Range: 1.3269. Min Range: -1.3269

Max Act: 1.1063. Min Act: -0.0000

Data Index: 1881774 (The Pile)

Max Activating Token Index: 638

Text #8

Max Range: 1.3269. Min Range: -1.3269

Max Act: 1.0948. Min Act: -0.0000

Data Index: 297796 (The Pile)

Max Activating Token Index: 586

Text #9

Max Range: 1.3269. Min Range: -1.3269

Max Act: 1.1402. Min Act: -0.0000

Data Index: 1834926 (The Pile)

Max Activating Token Index: 495

Text #10

Max Range: 1.3269. Min Range: -1.3269

Max Act: 1.2420. Min Act: -0.0000

Data Index: 1653412 (The Pile)

Max Activating Token Index: 559

Text #11

Max Range: 1.3269. Min Range: -1.3269

Max Act: 1.0234. Min Act: -0.0000

Data Index: 1841376 (The Pile)

Max Activating Token Index: 974

Text #12

Max Range: 1.3269. Min Range: -1.3269

Max Act: 1.0742. Min Act: -0.0000

Data Index: 1076809 (The Pile)

Max Activating Token Index: 605

Text #13

Max Range: 1.3269. Min Range: -1.3269

Max Act: 1.0745. Min Act: -0.0000

Data Index: 133152 (The Pile)

Max Activating Token Index: 333

Text #14

Max Range: 1.3269. Min Range: -1.3269

Max Act: 1.0729. Min Act: -0.0000

Data Index: 1362878 (The Pile)

Max Activating Token Index: 686

Text #15

Max Range: 1.3269. Min Range: -1.3269

Max Act: 1.0692. Min Act: -0.0000

Data Index: 483981 (The Pile)

Max Activating Token Index: 557

Text #16

Max Range: 1.3269. Min Range: -1.3269

Max Act: 1.0412. Min Act: -0.0000

Data Index: 376472 (The Pile)

Max Activating Token Index: 748

Text #17

Max Range: 1.3269. Min Range: -1.3269

Max Act: 1.0107. Min Act: -0.0000

Data Index: 528125 (The Pile)

Max Activating Token Index: 618

Text #18

Max Range: 1.3269. Min Range: -1.3269

Max Act: 1.0478. Min Act: -0.0000

Data Index: 1514398 (The Pile)

Max Activating Token Index: 146

Text #19

Max Range: 1.3269. Min Range: -1.3269

Max Act: 1.0822. Min Act: -0.0000

Data Index: 803049 (The Pile)

Max Activating Token Index: 32