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

Dataset: The Pile

Neuron 2502 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: 0.9989. Min Range: -0.9989

Max Act: 0.9989. Min Act: -0.0000

Data Index: 1625226 (The Pile)

Max Activating Token Index: 536

Text #1

Max Range: 0.9989. Min Range: -0.9989

Max Act: 0.9847. Min Act: -0.0000

Data Index: 861039 (The Pile)

Max Activating Token Index: 644

Text #2

Max Range: 0.9989. Min Range: -0.9989

Max Act: 0.8215. Min Act: -0.0000

Data Index: 69688 (The Pile)

Max Activating Token Index: 528

Text #3

Max Range: 0.9989. Min Range: -0.9989

Max Act: 0.9758. Min Act: -0.0000

Data Index: 1200703 (The Pile)

Max Activating Token Index: 319

Text #4

Max Range: 0.9989. Min Range: -0.9989

Max Act: 0.8459. Min Act: -0.0000

Data Index: 1922599 (The Pile)

Max Activating Token Index: 162

Text #5

Max Range: 0.9989. Min Range: -0.9989

Max Act: 0.7815. Min Act: -0.0000

Data Index: 1060699 (The Pile)

Max Activating Token Index: 734

Text #6

Max Range: 0.9989. Min Range: -0.9989

Max Act: 0.9200. Min Act: -0.0000

Data Index: 803444 (The Pile)

Max Activating Token Index: 414

Text #7

Max Range: 0.9989. Min Range: -0.9989

Max Act: 0.8511. Min Act: -0.0000

Data Index: 1569063 (The Pile)

Max Activating Token Index: 568

Text #8

Max Range: 0.9989. Min Range: -0.9989

Max Act: 0.8724. Min Act: -0.0000

Data Index: 953518 (The Pile)

Max Activating Token Index: 294

Text #9

Max Range: 0.9989. Min Range: -0.9989

Max Act: 0.7977. Min Act: -0.0000

Data Index: 72029 (The Pile)

Max Activating Token Index: 586

Text #10

Max Range: 0.9989. Min Range: -0.9989

Max Act: 0.8102. Min Act: -0.0000

Data Index: 1426620 (The Pile)

Max Activating Token Index: 322

Text #11

Max Range: 0.9989. Min Range: -0.9989

Max Act: 0.8158. Min Act: -0.0000

Data Index: 96621 (The Pile)

Max Activating Token Index: 561

Text #12

Max Range: 0.9989. Min Range: -0.9989

Max Act: 0.7807. Min Act: -0.0000

Data Index: 160898 (The Pile)

Max Activating Token Index: 1003

Text #13

Max Range: 0.9989. Min Range: -0.9989

Max Act: 0.8539. Min Act: -0.0000

Data Index: 1750296 (The Pile)

Max Activating Token Index: 417

Text #14

Max Range: 0.9989. Min Range: -0.9989

Max Act: 0.7591. Min Act: -0.0000

Data Index: 117985 (The Pile)

Max Activating Token Index: 256

Text #15

Max Range: 0.9989. Min Range: -0.9989

Max Act: 0.7755. Min Act: -0.0000

Data Index: 717749 (The Pile)

Max Activating Token Index: 125

Text #16

Max Range: 0.9989. Min Range: -0.9989

Max Act: 0.7725. Min Act: -0.0000

Data Index: 1995440 (The Pile)

Max Activating Token Index: 463

Text #17

Max Range: 0.9989. Min Range: -0.9989

Max Act: 0.7523. Min Act: -0.0000

Data Index: 307628 (The Pile)

Max Activating Token Index: 655

Text #18

Max Range: 0.9989. Min Range: -0.9989

Max Act: 0.6479. Min Act: -0.0000

Data Index: 223920 (The Pile)

Max Activating Token Index: 497

Text #19

Max Range: 0.9989. Min Range: -0.9989

Max Act: 0.8571. Min Act: -0.0000

Data Index: 762392 (The Pile)

Max Activating Token Index: 667