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

Dataset: The Pile

Neuron 525 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.8224. Min Act: -0.0000

Data Index: 1651739 (The Pile)

Max Activating Token Index: 743

Text #1

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.8184. Min Act: -0.0000

Data Index: 1455051 (The Pile)

Max Activating Token Index: 369

Text #2

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.8118. Min Act: -0.0000

Data Index: 25870 (The Pile)

Max Activating Token Index: 350

Text #3

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7804. Min Act: -0.0000

Data Index: 672954 (The Pile)

Max Activating Token Index: 128

Text #4

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.8029. Min Act: -0.0000

Data Index: 902985 (The Pile)

Max Activating Token Index: 355

Text #5

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7789. Min Act: -0.0000

Data Index: 792909 (The Pile)

Max Activating Token Index: 231

Text #6

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.8108. Min Act: -0.0000

Data Index: 761988 (The Pile)

Max Activating Token Index: 283

Text #7

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.8227. Min Act: -0.0000

Data Index: 642820 (The Pile)

Max Activating Token Index: 294

Text #8

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7928. Min Act: -0.0000

Data Index: 512010 (The Pile)

Max Activating Token Index: 237

Text #9

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7932. Min Act: -0.0000

Data Index: 1164636 (The Pile)

Max Activating Token Index: 307

Text #10

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7813. Min Act: -0.0000

Data Index: 730208 (The Pile)

Max Activating Token Index: 206

Text #11

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7815. Min Act: -0.0000

Data Index: 1117696 (The Pile)

Max Activating Token Index: 420

Text #12

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7576. Min Act: -0.0000

Data Index: 991605 (The Pile)

Max Activating Token Index: 836

Text #13

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7962. Min Act: -0.0000

Data Index: 1454428 (The Pile)

Max Activating Token Index: 112

Text #14

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7449. Min Act: -0.0000

Data Index: 355685 (The Pile)

Max Activating Token Index: 428

Text #15

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7715. Min Act: -0.0000

Data Index: 188906 (The Pile)

Max Activating Token Index: 850

Text #16

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7522. Min Act: -0.0000

Data Index: 463149 (The Pile)

Max Activating Token Index: 253

Text #17

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7690. Min Act: -0.0000

Data Index: 1036558 (The Pile)

Max Activating Token Index: 198

Text #18

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7333. Min Act: -0.0000

Data Index: 338267 (The Pile)

Max Activating Token Index: 1001

Text #19

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7534. Min Act: -0.0000

Data Index: 1189869 (The Pile)

Max Activating Token Index: 235