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

Dataset: The Pile

Neuron 3636 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.9715. Min Act: -0.0000

Data Index: 422089 (The Pile)

Max Activating Token Index: 537

Text #1

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.8517. Min Act: -0.0000

Data Index: 1540584 (The Pile)

Max Activating Token Index: 641

Text #2

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.8886. Min Act: -0.0000

Data Index: 1716026 (The Pile)

Max Activating Token Index: 482

Text #3

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.9336. Min Act: -0.0000

Data Index: 93640 (The Pile)

Max Activating Token Index: 521

Text #4

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.8816. Min Act: -0.0000

Data Index: 1027784 (The Pile)

Max Activating Token Index: 729

Text #5

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.8191. Min Act: -0.0000

Data Index: 605035 (The Pile)

Max Activating Token Index: 633

Text #6

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.8889. Min Act: -0.0000

Data Index: 1328933 (The Pile)

Max Activating Token Index: 589

Text #7

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.8457. Min Act: -0.0000

Data Index: 1514505 (The Pile)

Max Activating Token Index: 588

Text #8

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.8528. Min Act: -0.0000

Data Index: 1460851 (The Pile)

Max Activating Token Index: 649

Text #9

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.8714. Min Act: -0.0000

Data Index: 355763 (The Pile)

Max Activating Token Index: 636

Text #10

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.8737. Min Act: -0.0000

Data Index: 1845536 (The Pile)

Max Activating Token Index: 679

Text #11

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.7953. Min Act: -0.0000

Data Index: 909414 (The Pile)

Max Activating Token Index: 409

Text #12

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.8490. Min Act: -0.0000

Data Index: 1723163 (The Pile)

Max Activating Token Index: 541

Text #13

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.8613. Min Act: -0.0000

Data Index: 1435470 (The Pile)

Max Activating Token Index: 834

Text #14

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.8304. Min Act: -0.0000

Data Index: 1556569 (The Pile)

Max Activating Token Index: 428

Text #15

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.8095. Min Act: -0.0000

Data Index: 427883 (The Pile)

Max Activating Token Index: 476

Text #16

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.8170. Min Act: -0.0000

Data Index: 1479299 (The Pile)

Max Activating Token Index: 436

Text #17

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.8698. Min Act: -0.0000

Data Index: 33345 (The Pile)

Max Activating Token Index: 223

Text #18

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.8430. Min Act: -0.0000

Data Index: 1852817 (The Pile)

Max Activating Token Index: 363

Text #19

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.8160. Min Act: -0.0000

Data Index: 1762541 (The Pile)

Max Activating Token Index: 418