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

Dataset: The Pile

Neuron 766 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: 0.2860. Min Range: -0.2860

Max Act: 0.2557. Min Act: -0.0000

Data Index: 1542365 (The Pile)

Max Activating Token Index: 747

Text #1

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2736. Min Act: -0.0000

Data Index: 973775 (The Pile)

Max Activating Token Index: 466

Text #2

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2860. Min Act: -0.0000

Data Index: 1827483 (The Pile)

Max Activating Token Index: 545

Text #3

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2418. Min Act: 0.0000

Data Index: 438844 (The Pile)

Max Activating Token Index: 561

Text #4

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2600. Min Act: 0.0000

Data Index: 775423 (The Pile)

Max Activating Token Index: 695

Text #5

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2548. Min Act: -0.0000

Data Index: 1098729 (The Pile)

Max Activating Token Index: 587

Text #6

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2688. Min Act: -0.0000

Data Index: 1453574 (The Pile)

Max Activating Token Index: 551

Text #7

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2548. Min Act: 0.0000

Data Index: 1391395 (The Pile)

Max Activating Token Index: 521

Text #8

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2277. Min Act: -0.0000

Data Index: 1532114 (The Pile)

Max Activating Token Index: 677

Text #9

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2514. Min Act: 0.0000

Data Index: 1781035 (The Pile)

Max Activating Token Index: 949

Text #10

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2474. Min Act: -0.0000

Data Index: 1613555 (The Pile)

Max Activating Token Index: 599

Text #11

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2360. Min Act: -0.0000

Data Index: 543433 (The Pile)

Max Activating Token Index: 332

Text #12

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2406. Min Act: -0.0000

Data Index: 1646927 (The Pile)

Max Activating Token Index: 551

Text #13

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2337. Min Act: 0.0000

Data Index: 1299382 (The Pile)

Max Activating Token Index: 247

Text #14

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2501. Min Act: -0.0000

Data Index: 102987 (The Pile)

Max Activating Token Index: 341

Text #15

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2389. Min Act: -0.0000

Data Index: 722396 (The Pile)

Max Activating Token Index: 243

Text #16

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2502. Min Act: 0.0000

Data Index: 320394 (The Pile)

Max Activating Token Index: 503

Text #17

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2386. Min Act: 0.0000

Data Index: 877424 (The Pile)

Max Activating Token Index: 575

Text #18

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2342. Min Act: -0.0000

Data Index: 1314932 (The Pile)

Max Activating Token Index: 341

Text #19

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2412. Min Act: -0.0000

Data Index: 1207325 (The Pile)

Max Activating Token Index: 455