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

Dataset: The Pile

Neuron 334 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.8062. Min Act: -0.0000

Data Index: 1762447 (The Pile)

Max Activating Token Index: 707

Text #1

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.8885. Min Act: -0.0000

Data Index: 928932 (The Pile)

Max Activating Token Index: 837

Text #2

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.6754. Min Act: -0.0000

Data Index: 378371 (The Pile)

Max Activating Token Index: 945

Text #3

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.6528. Min Act: -0.0000

Data Index: 1002908 (The Pile)

Max Activating Token Index: 932

Text #4

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.6547. Min Act: -0.0000

Data Index: 1608207 (The Pile)

Max Activating Token Index: 1021

Text #5

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.6400. Min Act: -0.0000

Data Index: 629138 (The Pile)

Max Activating Token Index: 718

Text #6

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.5552. Min Act: -0.0000

Data Index: 112641 (The Pile)

Max Activating Token Index: 750

Text #7

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.5750. Min Act: -0.0000

Data Index: 618912 (The Pile)

Max Activating Token Index: 522

Text #8

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.5279. Min Act: -0.0000

Data Index: 877385 (The Pile)

Max Activating Token Index: 886

Text #9

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.5655. Min Act: -0.0000

Data Index: 1643506 (The Pile)

Max Activating Token Index: 39

Text #10

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.5421. Min Act: -0.0000

Data Index: 1207931 (The Pile)

Max Activating Token Index: 191

Text #11

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.5249. Min Act: -0.0000

Data Index: 443014 (The Pile)

Max Activating Token Index: 554

Text #12

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.5438. Min Act: -0.0000

Data Index: 1979649 (The Pile)

Max Activating Token Index: 136

Text #13

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.4600. Min Act: -0.0000

Data Index: 691002 (The Pile)

Max Activating Token Index: 590

Text #14

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.5314. Min Act: -0.0000

Data Index: 1738872 (The Pile)

Max Activating Token Index: 298

Text #15

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.5313. Min Act: -0.0000

Data Index: 1477124 (The Pile)

Max Activating Token Index: 274

Text #16

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.4954. Min Act: -0.0000

Data Index: 329411 (The Pile)

Max Activating Token Index: 812

Text #17

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.4912. Min Act: -0.0000

Data Index: 1941295 (The Pile)

Max Activating Token Index: 504

Text #18

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.4791. Min Act: -0.0000

Data Index: 939877 (The Pile)

Max Activating Token Index: 236

Text #19

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.5061. Min Act: -0.0000

Data Index: 1584212 (The Pile)

Max Activating Token Index: 563