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

Dataset: The Pile

Neuron 5025 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9679. Min Range: -1.9679

Max Act: 1.8780. Min Act: -0.0000

Data Index: 1772110 (The Pile)

Max Activating Token Index: 991

Text #1

Max Range: 1.9679. Min Range: -1.9679

Max Act: 1.7383. Min Act: -0.0000

Data Index: 1170870 (The Pile)

Max Activating Token Index: 702

Text #2

Max Range: 1.9679. Min Range: -1.9679

Max Act: 1.7422. Min Act: -0.0000

Data Index: 1485624 (The Pile)

Max Activating Token Index: 835

Text #3

Max Range: 1.9679. Min Range: -1.9679

Max Act: 1.5719. Min Act: -0.0000

Data Index: 1553196 (The Pile)

Max Activating Token Index: 467

Text #4

Max Range: 1.9679. Min Range: -1.9679

Max Act: 1.9552. Min Act: -0.0000

Data Index: 1489799 (The Pile)

Max Activating Token Index: 282

Text #5

Max Range: 1.9679. Min Range: -1.9679

Max Act: 1.7467. Min Act: -0.0000

Data Index: 1995296 (The Pile)

Max Activating Token Index: 61

Text #6

Max Range: 1.9679. Min Range: -1.9679

Max Act: 1.7393. Min Act: -0.0000

Data Index: 44141 (The Pile)

Max Activating Token Index: 361

Text #7

Max Range: 1.9679. Min Range: -1.9679

Max Act: 1.7418. Min Act: -0.0000

Data Index: 1027821 (The Pile)

Max Activating Token Index: 573

Text #8

Max Range: 1.9679. Min Range: -1.9679

Max Act: 1.6962. Min Act: -0.0000

Data Index: 931501 (The Pile)

Max Activating Token Index: 605

Text #9

Max Range: 1.9679. Min Range: -1.9679

Max Act: 1.5139. Min Act: -0.0000

Data Index: 1428716 (The Pile)

Max Activating Token Index: 195

Text #10

Max Range: 1.9679. Min Range: -1.9679

Max Act: 1.4352. Min Act: -0.0000

Data Index: 1362962 (The Pile)

Max Activating Token Index: 868

Text #11

Max Range: 1.9679. Min Range: -1.9679

Max Act: 1.8001. Min Act: -0.0000

Data Index: 1570589 (The Pile)

Max Activating Token Index: 697

Text #12

Max Range: 1.9679. Min Range: -1.9679

Max Act: 1.6393. Min Act: -0.0000

Data Index: 260775 (The Pile)

Max Activating Token Index: 172

Text #13

Max Range: 1.9679. Min Range: -1.9679

Max Act: 1.9679. Min Act: -0.0000

Data Index: 1006346 (The Pile)

Max Activating Token Index: 620

Text #14

Max Range: 1.9679. Min Range: -1.9679

Max Act: 1.6600. Min Act: -0.0000

Data Index: 1786076 (The Pile)

Max Activating Token Index: 611

Text #15

Max Range: 1.9679. Min Range: -1.9679

Max Act: 1.8373. Min Act: -0.0000

Data Index: 118309 (The Pile)

Max Activating Token Index: 240

Text #16

Max Range: 1.9679. Min Range: -1.9679

Max Act: 1.4633. Min Act: -0.0000

Data Index: 111326 (The Pile)

Max Activating Token Index: 652

Text #17

Max Range: 1.9679. Min Range: -1.9679

Max Act: 1.5349. Min Act: -0.0000

Data Index: 910156 (The Pile)

Max Activating Token Index: 853

Text #18

Max Range: 1.9679. Min Range: -1.9679

Max Act: 1.8010. Min Act: -0.0000

Data Index: 1208200 (The Pile)

Max Activating Token Index: 873

Text #19

Max Range: 1.9679. Min Range: -1.9679

Max Act: 1.5156. Min Act: -0.0000

Data Index: 1343369 (The Pile)

Max Activating Token Index: 870