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

Dataset: The Pile

Neuron 3189 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: 0.9886. Min Range: -0.9886

Max Act: 0.9598. Min Act: -0.0000

Data Index: 594949 (The Pile)

Max Activating Token Index: 238

Text #1

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.9534. Min Act: -0.0000

Data Index: 1229237 (The Pile)

Max Activating Token Index: 1018

Text #2

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.9124. Min Act: -0.0000

Data Index: 1742643 (The Pile)

Max Activating Token Index: 918

Text #3

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.9180. Min Act: -0.0000

Data Index: 637498 (The Pile)

Max Activating Token Index: 313

Text #4

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.8289. Min Act: -0.0000

Data Index: 1199012 (The Pile)

Max Activating Token Index: 649

Text #5

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.8785. Min Act: -0.0000

Data Index: 1487375 (The Pile)

Max Activating Token Index: 54

Text #6

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.9540. Min Act: -0.0000

Data Index: 396204 (The Pile)

Max Activating Token Index: 462

Text #7

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.9164. Min Act: -0.0000

Data Index: 907842 (The Pile)

Max Activating Token Index: 601

Text #8

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.9886. Min Act: -0.0000

Data Index: 241984 (The Pile)

Max Activating Token Index: 610

Text #9

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.9356. Min Act: -0.0000

Data Index: 1417551 (The Pile)

Max Activating Token Index: 651

Text #10

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.8719. Min Act: -0.0000

Data Index: 1194469 (The Pile)

Max Activating Token Index: 315

Text #11

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.7643. Min Act: -0.0000

Data Index: 541576 (The Pile)

Max Activating Token Index: 837

Text #12

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.8766. Min Act: -0.0000

Data Index: 775163 (The Pile)

Max Activating Token Index: 728

Text #13

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.8518. Min Act: -0.0000

Data Index: 1101268 (The Pile)

Max Activating Token Index: 25

Text #14

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.8750. Min Act: -0.0000

Data Index: 748740 (The Pile)

Max Activating Token Index: 556

Text #15

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.8511. Min Act: -0.0000

Data Index: 747786 (The Pile)

Max Activating Token Index: 731

Text #16

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.9147. Min Act: -0.0000

Data Index: 1873163 (The Pile)

Max Activating Token Index: 787

Text #17

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.8087. Min Act: -0.0000

Data Index: 1666785 (The Pile)

Max Activating Token Index: 713

Text #18

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.8222. Min Act: -0.0000

Data Index: 1261988 (The Pile)

Max Activating Token Index: 775

Text #19

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.8447. Min Act: -0.0000

Data Index: 747390 (The Pile)

Max Activating Token Index: 671