< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 5107 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.2670. Min Range: -1.2670

Max Act: 1.1886. Min Act: -0.0001

Data Index: 1767733 (The Pile)

Max Activating Token Index: 225

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.2670. Min Range: -1.2670

Max Act: 1.0720. Min Act: -0.0001

Data Index: 65848 (The Pile)

Max Activating Token Index: 674

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.2670. Min Range: -1.2670

Max Act: 1.2670. Min Act: -0.0001

Data Index: 1242197 (The Pile)

Max Activating Token Index: 638

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.2670. Min Range: -1.2670

Max Act: 1.1572. Min Act: -0.0001

Data Index: 926159 (The Pile)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.2670. Min Range: -1.2670

Max Act: 1.1656. Min Act: -0.0001

Data Index: 946421 (The Pile)

Max Activating Token Index: 904

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.2670. Min Range: -1.2670

Max Act: 1.1166. Min Act: -0.0001

Data Index: 1030370 (The Pile)

Max Activating Token Index: 300

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.2670. Min Range: -1.2670

Max Act: 1.0380. Min Act: -0.0001

Data Index: 1553205 (The Pile)

Max Activating Token Index: 333

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.2670. Min Range: -1.2670

Max Act: 1.0735. Min Act: -0.0001

Data Index: 550423 (The Pile)

Max Activating Token Index: 572

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.2670. Min Range: -1.2670

Max Act: 0.8603. Min Act: -0.0001

Data Index: 920959 (The Pile)

Max Activating Token Index: 972

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.2670. Min Range: -1.2670

Max Act: 0.8652. Min Act: -0.0001

Data Index: 1056446 (The Pile)

Max Activating Token Index: 523

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.2670. Min Range: -1.2670

Max Act: 0.9477. Min Act: -0.0001

Data Index: 1073650 (The Pile)

Max Activating Token Index: 495

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.2670. Min Range: -1.2670

Max Act: 0.8602. Min Act: -0.0001

Data Index: 19756 (The Pile)

Max Activating Token Index: 674

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.2670. Min Range: -1.2670

Max Act: 0.8878. Min Act: -0.0001

Data Index: 1945787 (The Pile)

Max Activating Token Index: 271

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.2670. Min Range: -1.2670

Max Act: 0.8704. Min Act: -0.0001

Data Index: 291470 (The Pile)

Max Activating Token Index: 467

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.2670. Min Range: -1.2670

Max Act: 0.8667. Min Act: -0.0001

Data Index: 466701 (The Pile)

Max Activating Token Index: 576

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.2670. Min Range: -1.2670

Max Act: 0.8963. Min Act: -0.0001

Data Index: 1388175 (The Pile)

Max Activating Token Index: 733

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.2670. Min Range: -1.2670

Max Act: 0.8198. Min Act: -0.0001

Data Index: 571666 (The Pile)

Max Activating Token Index: 468

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.2670. Min Range: -1.2670

Max Act: 0.7991. Min Act: -0.0001

Data Index: 413661 (The Pile)

Max Activating Token Index: 476

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.2670. Min Range: -1.2670

Max Act: 0.8585. Min Act: -0.0001

Data Index: 838813 (The Pile)

Max Activating Token Index: 109

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.2670. Min Range: -1.2670

Max Act: 0.8064. Min Act: -0.0001

Data Index: 840462 (The Pile)

Max Activating Token Index: 580

Click toggle to see full text

Truncated

Full Text #19