< Prev | Home | Model | Random | Next >

Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 3067 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')



Text #0

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.2311. Min Act: -0.0001

Data Index: 1876775 (The Pile)

Max Activating Token Index: 84

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.2354. Min Act: -0.0001

Data Index: 1624543 (The Pile)

Max Activating Token Index: 463

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.2222. Min Act: -0.0001

Data Index: 1551539 (The Pile)

Max Activating Token Index: 644

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.2169. Min Act: -0.0001

Data Index: 1932203 (The Pile)

Max Activating Token Index: 796

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.2129. Min Act: -0.0000

Data Index: 595033 (The Pile)

Max Activating Token Index: 999

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.2260. Min Act: -0.0001

Data Index: 268083 (The Pile)

Max Activating Token Index: 533

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.2076. Min Act: -0.0000

Data Index: 1697040 (The Pile)

Max Activating Token Index: 934

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.2096. Min Act: -0.0000

Data Index: 1526443 (The Pile)

Max Activating Token Index: 478

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.2061. Min Act: -0.0000

Data Index: 1327574 (The Pile)

Max Activating Token Index: 560

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1974. Min Act: -0.0001

Data Index: 1005403 (The Pile)

Max Activating Token Index: 198

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.2078. Min Act: -0.0001

Data Index: 644071 (The Pile)

Max Activating Token Index: 360

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.2038. Min Act: -0.0000

Data Index: 1254897 (The Pile)

Max Activating Token Index: 803

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1914. Min Act: -0.0001

Data Index: 373274 (The Pile)

Max Activating Token Index: 165

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1963. Min Act: -0.0000

Data Index: 1501554 (The Pile)

Max Activating Token Index: 898

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.2018. Min Act: -0.0001

Data Index: 1584390 (The Pile)

Max Activating Token Index: 171

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1953. Min Act: -0.0001

Data Index: 1594462 (The Pile)

Max Activating Token Index: 452

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.2002. Min Act: -0.0001

Data Index: 1275909 (The Pile)

Max Activating Token Index: 432

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1878. Min Act: -0.0001

Data Index: 294877 (The Pile)

Max Activating Token Index: 213

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1912. Min Act: -0.0001

Data Index: 1920945 (The Pile)

Max Activating Token Index: 377

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1913. Min Act: -0.0000

Data Index: 763720 (The Pile)

Max Activating Token Index: 494

Click toggle to see full text

Truncated

Full Text #19