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

Dataset: The Pile

Neuron 3247 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: 1.1662. Min Range: -1.1662

Max Act: 1.1662. Min Act: -0.0000

Data Index: 860949 (The Pile)

Max Activating Token Index: 726

Text #1

Max Range: 1.1662. Min Range: -1.1662

Max Act: 0.9833. Min Act: -0.0000

Data Index: 1845185 (The Pile)

Max Activating Token Index: 839

Text #2

Max Range: 1.1662. Min Range: -1.1662

Max Act: 1.0337. Min Act: -0.0000

Data Index: 1366740 (The Pile)

Max Activating Token Index: 518

Text #3

Max Range: 1.1662. Min Range: -1.1662

Max Act: 1.0356. Min Act: -0.0000

Data Index: 236867 (The Pile)

Max Activating Token Index: 852

Text #4

Max Range: 1.1662. Min Range: -1.1662

Max Act: 0.9464. Min Act: -0.0000

Data Index: 44103 (The Pile)

Max Activating Token Index: 501

Text #5

Max Range: 1.1662. Min Range: -1.1662

Max Act: 1.0855. Min Act: -0.0000

Data Index: 721694 (The Pile)

Max Activating Token Index: 565

Text #6

Max Range: 1.1662. Min Range: -1.1662

Max Act: 0.9958. Min Act: -0.0000

Data Index: 1567240 (The Pile)

Max Activating Token Index: 656

Text #7

Max Range: 1.1662. Min Range: -1.1662

Max Act: 1.0023. Min Act: -0.0000

Data Index: 385803 (The Pile)

Max Activating Token Index: 558

Text #8

Max Range: 1.1662. Min Range: -1.1662

Max Act: 0.9864. Min Act: -0.0000

Data Index: 1192090 (The Pile)

Max Activating Token Index: 588

Text #9

Max Range: 1.1662. Min Range: -1.1662

Max Act: 0.9775. Min Act: -0.0000

Data Index: 1763394 (The Pile)

Max Activating Token Index: 468

Text #10

Max Range: 1.1662. Min Range: -1.1662

Max Act: 0.9702. Min Act: -0.0000

Data Index: 1856731 (The Pile)

Max Activating Token Index: 549

Text #11

Max Range: 1.1662. Min Range: -1.1662

Max Act: 0.9236. Min Act: -0.0000

Data Index: 1221615 (The Pile)

Max Activating Token Index: 438

Text #12

Max Range: 1.1662. Min Range: -1.1662

Max Act: 0.9275. Min Act: -0.0000

Data Index: 861084 (The Pile)

Max Activating Token Index: 894

Text #13

Max Range: 1.1662. Min Range: -1.1662

Max Act: 0.8842. Min Act: -0.0000

Data Index: 1969717 (The Pile)

Max Activating Token Index: 780

Text #14

Max Range: 1.1662. Min Range: -1.1662

Max Act: 0.9411. Min Act: -0.0000

Data Index: 185519 (The Pile)

Max Activating Token Index: 497

Text #15

Max Range: 1.1662. Min Range: -1.1662

Max Act: 0.8656. Min Act: -0.0000

Data Index: 1181908 (The Pile)

Max Activating Token Index: 885

Text #16

Max Range: 1.1662. Min Range: -1.1662

Max Act: 0.9285. Min Act: -0.0000

Data Index: 1098934 (The Pile)

Max Activating Token Index: 490

Text #17

Max Range: 1.1662. Min Range: -1.1662

Max Act: 0.8384. Min Act: -0.0000

Data Index: 691523 (The Pile)

Max Activating Token Index: 667

Text #18

Max Range: 1.1662. Min Range: -1.1662

Max Act: 0.8650. Min Act: -0.0000

Data Index: 1124821 (The Pile)

Max Activating Token Index: 811

Text #19

Max Range: 1.1662. Min Range: -1.1662

Max Act: 0.9168. Min Act: -0.0000

Data Index: 853544 (The Pile)

Max Activating Token Index: 700