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

Dataset: The Pile

Neuron 4585 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.1023. Min Act: -0.0000

Data Index: 631350 (The Pile)

Max Activating Token Index: 967

Text #1

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0947. Min Act: -0.0000

Data Index: 722464 (The Pile)

Max Activating Token Index: 855

Text #2

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0821. Min Act: -0.0000

Data Index: 217356 (The Pile)

Max Activating Token Index: 290

Text #3

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0885. Min Act: 0.0000

Data Index: 1565394 (The Pile)

Max Activating Token Index: 917

Text #4

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0767. Min Act: -0.0000

Data Index: 315267 (The Pile)

Max Activating Token Index: 473

Text #5

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0780. Min Act: -0.0000

Data Index: 1173196 (The Pile)

Max Activating Token Index: 573

Text #6

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0742. Min Act: -0.0000

Data Index: 541267 (The Pile)

Max Activating Token Index: 433

Text #7

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0721. Min Act: -0.0000

Data Index: 658106 (The Pile)

Max Activating Token Index: 466

Text #8

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0682. Min Act: -0.0000

Data Index: 649719 (The Pile)

Max Activating Token Index: 914

Text #9

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0739. Min Act: -0.0000

Data Index: 1017562 (The Pile)

Max Activating Token Index: 73

Text #10

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0705. Min Act: -0.0000

Data Index: 1584144 (The Pile)

Max Activating Token Index: 463

Text #11

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0702. Min Act: -0.0000

Data Index: 1938512 (The Pile)

Max Activating Token Index: 288

Text #12

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0666. Min Act: -0.0000

Data Index: 1372947 (The Pile)

Max Activating Token Index: 958

Text #13

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0667. Min Act: -0.0000

Data Index: 134418 (The Pile)

Max Activating Token Index: 389

Text #14

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0651. Min Act: -0.0000

Data Index: 1196533 (The Pile)

Max Activating Token Index: 727

Text #15

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0671. Min Act: -0.0000

Data Index: 363558 (The Pile)

Max Activating Token Index: 181

Text #16

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0642. Min Act: -0.0000

Data Index: 1802567 (The Pile)

Max Activating Token Index: 303

Text #17

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0662. Min Act: -0.0000

Data Index: 470654 (The Pile)

Max Activating Token Index: 327

Text #18

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0639. Min Act: -0.0000

Data Index: 777685 (The Pile)

Max Activating Token Index: 345

Text #19

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0655. Min Act: -0.0000

Data Index: 1059911 (The Pile)

Max Activating Token Index: 765