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

Dataset: The Pile

Neuron 643 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8865. Min Range: -0.8865

Max Act: 0.8865. Min Act: -0.0000

Data Index: 1710029 (The Pile)

Max Activating Token Index: 476

Text #1

Max Range: 0.8865. Min Range: -0.8865

Max Act: 0.6779. Min Act: 0.0000

Data Index: 1787365 (The Pile)

Max Activating Token Index: 885

Text #2

Max Range: 0.8865. Min Range: -0.8865

Max Act: 0.7729. Min Act: -0.0000

Data Index: 111672 (The Pile)

Max Activating Token Index: 422

Text #3

Max Range: 0.8865. Min Range: -0.8865

Max Act: 0.8196. Min Act: -0.0000

Data Index: 1747947 (The Pile)

Max Activating Token Index: 481

Text #4

Max Range: 0.8865. Min Range: -0.8865

Max Act: 0.7300. Min Act: 0.0000

Data Index: 298212 (The Pile)

Max Activating Token Index: 969

Text #5

Max Range: 0.8865. Min Range: -0.8865

Max Act: 0.7600. Min Act: -0.0000

Data Index: 529295 (The Pile)

Max Activating Token Index: 172

Text #6

Max Range: 0.8865. Min Range: -0.8865

Max Act: 0.6775. Min Act: -0.0000

Data Index: 42295 (The Pile)

Max Activating Token Index: 617

Text #7

Max Range: 0.8865. Min Range: -0.8865

Max Act: 0.6914. Min Act: -0.0000

Data Index: 1506137 (The Pile)

Max Activating Token Index: 382

Text #8

Max Range: 0.8865. Min Range: -0.8865

Max Act: 0.6864. Min Act: 0.0000

Data Index: 1026857 (The Pile)

Max Activating Token Index: 125

Text #9

Max Range: 0.8865. Min Range: -0.8865

Max Act: 0.6787. Min Act: -0.0000

Data Index: 1344383 (The Pile)

Max Activating Token Index: 687

Text #10

Max Range: 0.8865. Min Range: -0.8865

Max Act: 0.6562. Min Act: -0.0000

Data Index: 1180030 (The Pile)

Max Activating Token Index: 765

Text #11

Max Range: 0.8865. Min Range: -0.8865

Max Act: 0.6737. Min Act: -0.0000

Data Index: 1797809 (The Pile)

Max Activating Token Index: 525

Text #12

Max Range: 0.8865. Min Range: -0.8865

Max Act: 0.7080. Min Act: -0.0000

Data Index: 1325581 (The Pile)

Max Activating Token Index: 23

Text #13

Max Range: 0.8865. Min Range: -0.8865

Max Act: 0.6317. Min Act: -0.0000

Data Index: 629209 (The Pile)

Max Activating Token Index: 1009

Text #14

Max Range: 0.8865. Min Range: -0.8865

Max Act: 0.6235. Min Act: -0.0000

Data Index: 480000 (The Pile)

Max Activating Token Index: 485

Text #15

Max Range: 0.8865. Min Range: -0.8865

Max Act: 0.6634. Min Act: -0.0000

Data Index: 385579 (The Pile)

Max Activating Token Index: 120

Text #16

Max Range: 0.8865. Min Range: -0.8865

Max Act: 0.6177. Min Act: -0.0000

Data Index: 835262 (The Pile)

Max Activating Token Index: 294

Text #17

Max Range: 0.8865. Min Range: -0.8865

Max Act: 0.6765. Min Act: -0.0000

Data Index: 337280 (The Pile)

Max Activating Token Index: 511

Text #18

Max Range: 0.8865. Min Range: -0.8865

Max Act: 0.5893. Min Act: -0.0000

Data Index: 1443785 (The Pile)

Max Activating Token Index: 907

Text #19

Max Range: 0.8865. Min Range: -0.8865

Max Act: 0.5993. Min Act: -0.0000

Data Index: 240327 (The Pile)

Max Activating Token Index: 569