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

Dataset: The Pile

Neuron 1158 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: 0.3597. Min Range: -0.3597

Max Act: 0.3453. Min Act: -0.0000

Data Index: 1487588 (The Pile)

Max Activating Token Index: 900

Text #1

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.3481. Min Act: -0.0000

Data Index: 1928780 (The Pile)

Max Activating Token Index: 518

Text #2

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.3597. Min Act: -0.0000

Data Index: 68295 (The Pile)

Max Activating Token Index: 882

Text #3

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.3469. Min Act: -0.0000

Data Index: 1535540 (The Pile)

Max Activating Token Index: 852

Text #4

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.3168. Min Act: -0.0000

Data Index: 1491441 (The Pile)

Max Activating Token Index: 792

Text #5

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.2996. Min Act: -0.0000

Data Index: 1694977 (The Pile)

Max Activating Token Index: 710

Text #6

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.2874. Min Act: -0.0000

Data Index: 1604351 (The Pile)

Max Activating Token Index: 462

Text #7

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.2837. Min Act: -0.0000

Data Index: 1211424 (The Pile)

Max Activating Token Index: 841

Text #8

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.2573. Min Act: -0.0000

Data Index: 1903743 (The Pile)

Max Activating Token Index: 401

Text #9

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.3044. Min Act: -0.0000

Data Index: 1587688 (The Pile)

Max Activating Token Index: 627

Text #10

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.2753. Min Act: -0.0000

Data Index: 1462403 (The Pile)

Max Activating Token Index: 370

Text #11

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.2845. Min Act: -0.0000

Data Index: 933978 (The Pile)

Max Activating Token Index: 392

Text #12

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.2740. Min Act: -0.0000

Data Index: 397640 (The Pile)

Max Activating Token Index: 689

Text #13

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.2698. Min Act: -0.0000

Data Index: 1675076 (The Pile)

Max Activating Token Index: 482

Text #14

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.3006. Min Act: -0.0000

Data Index: 1554792 (The Pile)

Max Activating Token Index: 1004

Text #15

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.2775. Min Act: -0.0000

Data Index: 1491558 (The Pile)

Max Activating Token Index: 618

Text #16

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.2619. Min Act: -0.0000

Data Index: 1458125 (The Pile)

Max Activating Token Index: 277

Text #17

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.2797. Min Act: -0.0000

Data Index: 749598 (The Pile)

Max Activating Token Index: 909

Text #18

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.2612. Min Act: -0.0000

Data Index: 418341 (The Pile)

Max Activating Token Index: 571

Text #19

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.2748. Min Act: -0.0000

Data Index: 271120 (The Pile)

Max Activating Token Index: 204