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

Dataset: The Pile

Neuron 1167 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9412. Min Range: -0.9412

Max Act: 0.9412. Min Act: -0.0000

Data Index: 1156176 (The Pile)

Max Activating Token Index: 734

Text #1

Max Range: 0.9412. Min Range: -0.9412

Max Act: 0.8925. Min Act: -0.0000

Data Index: 1726875 (The Pile)

Max Activating Token Index: 754

Text #2

Max Range: 0.9412. Min Range: -0.9412

Max Act: 0.8480. Min Act: -0.0000

Data Index: 432958 (The Pile)

Max Activating Token Index: 505

Text #3

Max Range: 0.9412. Min Range: -0.9412

Max Act: 0.8135. Min Act: -0.0000

Data Index: 848386 (The Pile)

Max Activating Token Index: 344

Text #4

Max Range: 0.9412. Min Range: -0.9412

Max Act: 0.7606. Min Act: -0.0000

Data Index: 377763 (The Pile)

Max Activating Token Index: 626

Text #5

Max Range: 0.9412. Min Range: -0.9412

Max Act: 0.7134. Min Act: -0.0000

Data Index: 1103718 (The Pile)

Max Activating Token Index: 422

Text #6

Max Range: 0.9412. Min Range: -0.9412

Max Act: 0.6815. Min Act: -0.0000

Data Index: 300382 (The Pile)

Max Activating Token Index: 666

Text #7

Max Range: 0.9412. Min Range: -0.9412

Max Act: 0.7333. Min Act: -0.0000

Data Index: 56555 (The Pile)

Max Activating Token Index: 685

Text #8

Max Range: 0.9412. Min Range: -0.9412

Max Act: 0.6803. Min Act: -0.0000

Data Index: 612350 (The Pile)

Max Activating Token Index: 665

Text #9

Max Range: 0.9412. Min Range: -0.9412

Max Act: 0.6882. Min Act: -0.0000

Data Index: 1412763 (The Pile)

Max Activating Token Index: 701

Text #10

Max Range: 0.9412. Min Range: -0.9412

Max Act: 0.6739. Min Act: -0.0000

Data Index: 1901743 (The Pile)

Max Activating Token Index: 570

Text #11

Max Range: 0.9412. Min Range: -0.9412

Max Act: 0.6716. Min Act: -0.0000

Data Index: 264226 (The Pile)

Max Activating Token Index: 256

Text #12

Max Range: 0.9412. Min Range: -0.9412

Max Act: 0.6378. Min Act: -0.0000

Data Index: 1538899 (The Pile)

Max Activating Token Index: 546

Text #13

Max Range: 0.9412. Min Range: -0.9412

Max Act: 0.5814. Min Act: -0.0000

Data Index: 114260 (The Pile)

Max Activating Token Index: 689

Text #14

Max Range: 0.9412. Min Range: -0.9412

Max Act: 0.6122. Min Act: -0.0000

Data Index: 21603 (The Pile)

Max Activating Token Index: 627

Text #15

Max Range: 0.9412. Min Range: -0.9412

Max Act: 0.6062. Min Act: -0.0000

Data Index: 640865 (The Pile)

Max Activating Token Index: 144

Text #16

Max Range: 0.9412. Min Range: -0.9412

Max Act: 0.5324. Min Act: -0.0000

Data Index: 95922 (The Pile)

Max Activating Token Index: 123

Text #17

Max Range: 0.9412. Min Range: -0.9412

Max Act: 0.5288. Min Act: -0.0000

Data Index: 1078183 (The Pile)

Max Activating Token Index: 635

Text #18

Max Range: 0.9412. Min Range: -0.9412

Max Act: 0.5413. Min Act: -0.0000

Data Index: 1732690 (The Pile)

Max Activating Token Index: 631

Text #19

Max Range: 0.9412. Min Range: -0.9412

Max Act: 0.5157. Min Act: -0.0000

Data Index: 883615 (The Pile)

Max Activating Token Index: 131