< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 4095 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')



Text #0

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.2668. Min Act: -0.0001

Data Index: 1574831 (The Pile)

Max Activating Token Index: 243

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.2262. Min Act: -0.0001

Data Index: 1417311 (The Pile)

Max Activating Token Index: 488

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.2504. Min Act: -0.0001

Data Index: 232608 (The Pile)

Max Activating Token Index: 927

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.2270. Min Act: -0.0001

Data Index: 1410466 (The Pile)

Max Activating Token Index: 218

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.2413. Min Act: -0.0001

Data Index: 1343382 (The Pile)

Max Activating Token Index: 747

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.2155. Min Act: -0.0001

Data Index: 707793 (The Pile)

Max Activating Token Index: 585

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.2093. Min Act: -0.0001

Data Index: 1720313 (The Pile)

Max Activating Token Index: 491

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.1968. Min Act: -0.0001

Data Index: 741673 (The Pile)

Max Activating Token Index: 847

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.2048. Min Act: -0.0001

Data Index: 1465418 (The Pile)

Max Activating Token Index: 451

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.2081. Min Act: -0.0001

Data Index: 235419 (The Pile)

Max Activating Token Index: 416

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.1944. Min Act: -0.0001

Data Index: 752365 (The Pile)

Max Activating Token Index: 301

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.1927. Min Act: -0.0001

Data Index: 1813067 (The Pile)

Max Activating Token Index: 878

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.1915. Min Act: -0.0001

Data Index: 1700972 (The Pile)

Max Activating Token Index: 847

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.1982. Min Act: -0.0001

Data Index: 1058128 (The Pile)

Max Activating Token Index: 17

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.1958. Min Act: -0.0001

Data Index: 728752 (The Pile)

Max Activating Token Index: 183

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.2013. Min Act: -0.0001

Data Index: 1759004 (The Pile)

Max Activating Token Index: 247

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.2013. Min Act: -0.0001

Data Index: 1746349 (The Pile)

Max Activating Token Index: 476

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.1873. Min Act: -0.0001

Data Index: 1268993 (The Pile)

Max Activating Token Index: 579

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.1929. Min Act: -0.0001

Data Index: 1837762 (The Pile)

Max Activating Token Index: 814

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.1911. Min Act: -0.0001

Data Index: 625138 (The Pile)

Max Activating Token Index: 221

Click toggle to see full text

Truncated

Full Text #19