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

Dataset: The Pile

Neuron 1619 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.6631. Min Act: -0.0000

Data Index: 351164 (The Pile)

Max Activating Token Index: 396

Text #1

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.6893. Min Act: -0.0000

Data Index: 736631 (The Pile)

Max Activating Token Index: 696

Text #2

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.5984. Min Act: -0.0000

Data Index: 1608072 (The Pile)

Max Activating Token Index: 833

Text #3

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.6446. Min Act: -0.0000

Data Index: 1661444 (The Pile)

Max Activating Token Index: 539

Text #4

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.6408. Min Act: -0.0000

Data Index: 95787 (The Pile)

Max Activating Token Index: 248

Text #5

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.6288. Min Act: -0.0000

Data Index: 816608 (The Pile)

Max Activating Token Index: 142

Text #6

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.6009. Min Act: -0.0000

Data Index: 1315906 (The Pile)

Max Activating Token Index: 615

Text #7

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.6208. Min Act: -0.0000

Data Index: 1442420 (The Pile)

Max Activating Token Index: 804

Text #8

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.6214. Min Act: -0.0000

Data Index: 705133 (The Pile)

Max Activating Token Index: 307

Text #9

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.6036. Min Act: -0.0000

Data Index: 487394 (The Pile)

Max Activating Token Index: 261

Text #10

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.5704. Min Act: -0.0000

Data Index: 1579402 (The Pile)

Max Activating Token Index: 521

Text #11

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.5962. Min Act: -0.0000

Data Index: 1080782 (The Pile)

Max Activating Token Index: 978

Text #12

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.5782. Min Act: -0.0000

Data Index: 1275722 (The Pile)

Max Activating Token Index: 66

Text #13

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.5615. Min Act: -0.0000

Data Index: 214983 (The Pile)

Max Activating Token Index: 642

Text #14

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.5800. Min Act: -0.0000

Data Index: 1438163 (The Pile)

Max Activating Token Index: 932

Text #15

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.5476. Min Act: -0.0000

Data Index: 1988072 (The Pile)

Max Activating Token Index: 639

Text #16

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.5800. Min Act: -0.0000

Data Index: 6893 (The Pile)

Max Activating Token Index: 256

Text #17

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.5414. Min Act: -0.0000

Data Index: 1624147 (The Pile)

Max Activating Token Index: 133

Text #18

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.5579. Min Act: -0.0000

Data Index: 430572 (The Pile)

Max Activating Token Index: 1011

Text #19

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.5670. Min Act: -0.0000

Data Index: 1272518 (The Pile)

Max Activating Token Index: 726