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

Dataset: The Pile

Neuron 3570 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: 0.5853. Min Range: -0.5853

Max Act: 0.5106. Min Act: -0.0000

Data Index: 859009 (The Pile)

Max Activating Token Index: 506

Text #1

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.5359. Min Act: -0.0000

Data Index: 1555097 (The Pile)

Max Activating Token Index: 570

Text #2

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.5853. Min Act: -0.0000

Data Index: 562531 (The Pile)

Max Activating Token Index: 273

Text #3

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.5392. Min Act: -0.0000

Data Index: 1197145 (The Pile)

Max Activating Token Index: 836

Text #4

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.5131. Min Act: -0.0000

Data Index: 88942 (The Pile)

Max Activating Token Index: 771

Text #5

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.5274. Min Act: -0.0000

Data Index: 1565016 (The Pile)

Max Activating Token Index: 614

Text #6

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.5555. Min Act: -0.0000

Data Index: 304888 (The Pile)

Max Activating Token Index: 819

Text #7

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.5121. Min Act: -0.0000

Data Index: 85779 (The Pile)

Max Activating Token Index: 683

Text #8

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.5051. Min Act: -0.0000

Data Index: 354415 (The Pile)

Max Activating Token Index: 122

Text #9

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.4837. Min Act: -0.0000

Data Index: 196525 (The Pile)

Max Activating Token Index: 320

Text #10

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.4869. Min Act: -0.0000

Data Index: 179788 (The Pile)

Max Activating Token Index: 420

Text #11

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.4967. Min Act: -0.0000

Data Index: 1089901 (The Pile)

Max Activating Token Index: 87

Text #12

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.5299. Min Act: -0.0000

Data Index: 1355114 (The Pile)

Max Activating Token Index: 420

Text #13

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.4808. Min Act: -0.0000

Data Index: 611607 (The Pile)

Max Activating Token Index: 682

Text #14

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.5088. Min Act: -0.0000

Data Index: 1026136 (The Pile)

Max Activating Token Index: 778

Text #15

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.4832. Min Act: -0.0000

Data Index: 515269 (The Pile)

Max Activating Token Index: 202

Text #16

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.5135. Min Act: -0.0000

Data Index: 986178 (The Pile)

Max Activating Token Index: 801

Text #17

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.4779. Min Act: -0.0000

Data Index: 244567 (The Pile)

Max Activating Token Index: 243

Text #18

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.4693. Min Act: -0.0000

Data Index: 470744 (The Pile)

Max Activating Token Index: 79

Text #19

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.4677. Min Act: -0.0000

Data Index: 1503108 (The Pile)

Max Activating Token Index: 451