< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 37 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: 6.0677. Min Range: -6.0677

Max Act: 6.0677. Min Act: -0.0000

Data Index: 1494049 (The Pile)

Max Activating Token Index: 858

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 6.0677. Min Range: -6.0677

Max Act: 5.1520. Min Act: -0.0000

Data Index: 1870852 (The Pile)

Max Activating Token Index: 677

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 6.0677. Min Range: -6.0677

Max Act: 5.6366. Min Act: -0.0000

Data Index: 1348086 (The Pile)

Max Activating Token Index: 401

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 6.0677. Min Range: -6.0677

Max Act: 5.2585. Min Act: -0.0000

Data Index: 919077 (The Pile)

Max Activating Token Index: 1004

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 6.0677. Min Range: -6.0677

Max Act: 4.8719. Min Act: -0.0000

Data Index: 1652799 (The Pile)

Max Activating Token Index: 832

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 6.0677. Min Range: -6.0677

Max Act: 5.2601. Min Act: -0.0000

Data Index: 301214 (The Pile)

Max Activating Token Index: 512

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 6.0677. Min Range: -6.0677

Max Act: 5.0354. Min Act: -0.0000

Data Index: 1305858 (The Pile)

Max Activating Token Index: 44

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 6.0677. Min Range: -6.0677

Max Act: 4.3694. Min Act: -0.0000

Data Index: 312135 (The Pile)

Max Activating Token Index: 209

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 6.0677. Min Range: -6.0677

Max Act: 5.0329. Min Act: -0.0000

Data Index: 1907952 (The Pile)

Max Activating Token Index: 336

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 6.0677. Min Range: -6.0677

Max Act: 4.8447. Min Act: -0.0000

Data Index: 1838565 (The Pile)

Max Activating Token Index: 519

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 6.0677. Min Range: -6.0677

Max Act: 4.8112. Min Act: -0.0000

Data Index: 1165595 (The Pile)

Max Activating Token Index: 360

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 6.0677. Min Range: -6.0677

Max Act: 5.7833. Min Act: -0.0000

Data Index: 599597 (The Pile)

Max Activating Token Index: 584

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 6.0677. Min Range: -6.0677

Max Act: 5.3134. Min Act: -0.0000

Data Index: 1253368 (The Pile)

Max Activating Token Index: 480

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 6.0677. Min Range: -6.0677

Max Act: 5.1065. Min Act: -0.0000

Data Index: 505161 (The Pile)

Max Activating Token Index: 118

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 6.0677. Min Range: -6.0677

Max Act: 4.9064. Min Act: -0.0000

Data Index: 207117 (The Pile)

Max Activating Token Index: 649

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 6.0677. Min Range: -6.0677

Max Act: 4.3921. Min Act: -0.0000

Data Index: 1639752 (The Pile)

Max Activating Token Index: 581

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 6.0677. Min Range: -6.0677

Max Act: 4.7077. Min Act: -0.0000

Data Index: 1489768 (The Pile)

Max Activating Token Index: 555

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 6.0677. Min Range: -6.0677

Max Act: 4.7513. Min Act: -0.0000

Data Index: 1979773 (The Pile)

Max Activating Token Index: 871

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 6.0677. Min Range: -6.0677

Max Act: 4.8710. Min Act: -0.0000

Data Index: 1617787 (The Pile)

Max Activating Token Index: 488

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 6.0677. Min Range: -6.0677

Max Act: 4.6224. Min Act: -0.0000

Data Index: 1159488 (The Pile)

Max Activating Token Index: 685

Click toggle to see full text

Truncated

Full Text #19