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

Dataset: The Pile

Neuron 2451 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3614. Min Range: -1.3614

Max Act: 1.3614. Min Act: -0.0000

Data Index: 208319 (The Pile)

Max Activating Token Index: 878

Text #1

Max Range: 1.3614. Min Range: -1.3614

Max Act: 1.1575. Min Act: -0.0000

Data Index: 569821 (The Pile)

Max Activating Token Index: 748

Text #2

Max Range: 1.3614. Min Range: -1.3614

Max Act: 1.0930. Min Act: -0.0000

Data Index: 592431 (The Pile)

Max Activating Token Index: 594

Text #3

Max Range: 1.3614. Min Range: -1.3614

Max Act: 1.0468. Min Act: -0.0000

Data Index: 1668635 (The Pile)

Max Activating Token Index: 94

Text #4

Max Range: 1.3614. Min Range: -1.3614

Max Act: 0.9108. Min Act: -0.0000

Data Index: 497369 (The Pile)

Max Activating Token Index: 745

Text #5

Max Range: 1.3614. Min Range: -1.3614

Max Act: 0.9535. Min Act: -0.0000

Data Index: 1721812 (The Pile)

Max Activating Token Index: 773

Text #6

Max Range: 1.3614. Min Range: -1.3614

Max Act: 0.8376. Min Act: -0.0000

Data Index: 1374274 (The Pile)

Max Activating Token Index: 510

Text #7

Max Range: 1.3614. Min Range: -1.3614

Max Act: 0.8293. Min Act: -0.0000

Data Index: 1596130 (The Pile)

Max Activating Token Index: 387

Text #8

Max Range: 1.3614. Min Range: -1.3614

Max Act: 0.7903. Min Act: -0.0000

Data Index: 1824839 (The Pile)

Max Activating Token Index: 191

Text #9

Max Range: 1.3614. Min Range: -1.3614

Max Act: 0.7686. Min Act: -0.0000

Data Index: 973616 (The Pile)

Max Activating Token Index: 39

Text #10

Max Range: 1.3614. Min Range: -1.3614

Max Act: 0.7505. Min Act: -0.0000

Data Index: 1499843 (The Pile)

Max Activating Token Index: 388

Text #11

Max Range: 1.3614. Min Range: -1.3614

Max Act: 0.7360. Min Act: -0.0000

Data Index: 901283 (The Pile)

Max Activating Token Index: 905

Text #12

Max Range: 1.3614. Min Range: -1.3614

Max Act: 0.7489. Min Act: -0.0000

Data Index: 336960 (The Pile)

Max Activating Token Index: 942

Text #13

Max Range: 1.3614. Min Range: -1.3614

Max Act: 0.7348. Min Act: -0.0000

Data Index: 1982789 (The Pile)

Max Activating Token Index: 639

Text #14

Max Range: 1.3614. Min Range: -1.3614

Max Act: 0.7483. Min Act: -0.0000

Data Index: 519445 (The Pile)

Max Activating Token Index: 907

Text #15

Max Range: 1.3614. Min Range: -1.3614

Max Act: 0.7899. Min Act: -0.0000

Data Index: 1468954 (The Pile)

Max Activating Token Index: 660

Text #16

Max Range: 1.3614. Min Range: -1.3614

Max Act: 0.7386. Min Act: -0.0000

Data Index: 865637 (The Pile)

Max Activating Token Index: 96

Text #17

Max Range: 1.3614. Min Range: -1.3614

Max Act: 0.7265. Min Act: -0.0000

Data Index: 1421353 (The Pile)

Max Activating Token Index: 592

Text #18

Max Range: 1.3614. Min Range: -1.3614

Max Act: 0.7776. Min Act: -0.0000

Data Index: 1339426 (The Pile)

Max Activating Token Index: 813

Text #19

Max Range: 1.3614. Min Range: -1.3614

Max Act: 0.7201. Min Act: -0.0000

Data Index: 971528 (The Pile)

Max Activating Token Index: 313