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

Dataset: The Pile

Neuron 2797 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: 0.6745. Min Range: -0.6745

Max Act: 0.6745. Min Act: -0.0000

Data Index: 240884 (The Pile)

Max Activating Token Index: 125

Text #1

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.6184. Min Act: -0.0000

Data Index: 1273491 (The Pile)

Max Activating Token Index: 806

Text #2

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5791. Min Act: -0.0000

Data Index: 1861038 (The Pile)

Max Activating Token Index: 811

Text #3

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5861. Min Act: -0.0000

Data Index: 1531852 (The Pile)

Max Activating Token Index: 256

Text #4

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.4927. Min Act: -0.0000

Data Index: 128223 (The Pile)

Max Activating Token Index: 302

Text #5

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.6267. Min Act: -0.0000

Data Index: 1889325 (The Pile)

Max Activating Token Index: 1016

Text #6

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.6354. Min Act: -0.0000

Data Index: 1531057 (The Pile)

Max Activating Token Index: 620

Text #7

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.6090. Min Act: -0.0000

Data Index: 882198 (The Pile)

Max Activating Token Index: 336

Text #8

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5895. Min Act: -0.0000

Data Index: 692832 (The Pile)

Max Activating Token Index: 247

Text #9

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5806. Min Act: -0.0000

Data Index: 1654749 (The Pile)

Max Activating Token Index: 283

Text #10

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5539. Min Act: -0.0000

Data Index: 593193 (The Pile)

Max Activating Token Index: 680

Text #11

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5453. Min Act: -0.0000

Data Index: 1070635 (The Pile)

Max Activating Token Index: 939

Text #12

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5357. Min Act: -0.0000

Data Index: 975866 (The Pile)

Max Activating Token Index: 660

Text #13

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5955. Min Act: -0.0000

Data Index: 332695 (The Pile)

Max Activating Token Index: 511

Text #14

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5366. Min Act: -0.0000

Data Index: 590610 (The Pile)

Max Activating Token Index: 890

Text #15

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5128. Min Act: -0.0000

Data Index: 424502 (The Pile)

Max Activating Token Index: 753

Text #16

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.4825. Min Act: -0.0000

Data Index: 312141 (The Pile)

Max Activating Token Index: 462

Text #17

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.4907. Min Act: -0.0000

Data Index: 1914592 (The Pile)

Max Activating Token Index: 32

Text #18

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5112. Min Act: -0.0000

Data Index: 1132237 (The Pile)

Max Activating Token Index: 259

Text #19

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.4812. Min Act: -0.0000

Data Index: 980638 (The Pile)

Max Activating Token Index: 856