< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 4063 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.8967. Min Act: -0.0001

Data Index: 234611 (The Pile)

Max Activating Token Index: 537

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.5925. Min Act: -0.0001

Data Index: 1833966 (The Pile)

Max Activating Token Index: 82

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.1929. Min Act: -0.0001

Data Index: 1790941 (The Pile)

Max Activating Token Index: 312

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.3274. Min Act: -0.0001

Data Index: 1883827 (The Pile)

Max Activating Token Index: 645

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.1398. Min Act: -0.0001

Data Index: 232570 (The Pile)

Max Activating Token Index: 642

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.1503. Min Act: -0.0001

Data Index: 1646915 (The Pile)

Max Activating Token Index: 158

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.1150. Min Act: -0.0001

Data Index: 24166 (The Pile)

Max Activating Token Index: 577

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.0419. Min Act: -0.0001

Data Index: 1538356 (The Pile)

Max Activating Token Index: 30

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.0917. Min Act: -0.0001

Data Index: 1362622 (The Pile)

Max Activating Token Index: 559

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.8967. Min Range: -1.8967

Max Act: 0.9397. Min Act: -0.0001

Data Index: 396930 (The Pile)

Max Activating Token Index: 315

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.8967. Min Range: -1.8967

Max Act: 0.8095. Min Act: -0.0001

Data Index: 1033426 (The Pile)

Max Activating Token Index: 601

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.8967. Min Range: -1.8967

Max Act: 0.7704. Min Act: -0.0001

Data Index: 560258 (The Pile)

Max Activating Token Index: 514

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.8967. Min Range: -1.8967

Max Act: 0.9298. Min Act: -0.0001

Data Index: 1441448 (The Pile)

Max Activating Token Index: 491

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.8967. Min Range: -1.8967

Max Act: 0.8318. Min Act: -0.0001

Data Index: 1429037 (The Pile)

Max Activating Token Index: 123

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.8967. Min Range: -1.8967

Max Act: 0.9890. Min Act: -0.0001

Data Index: 1794207 (The Pile)

Max Activating Token Index: 249

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.8967. Min Range: -1.8967

Max Act: 0.8589. Min Act: -0.0001

Data Index: 290627 (The Pile)

Max Activating Token Index: 415

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.8967. Min Range: -1.8967

Max Act: 0.8052. Min Act: -0.0001

Data Index: 84016 (The Pile)

Max Activating Token Index: 279

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.8967. Min Range: -1.8967

Max Act: 0.8113. Min Act: -0.0001

Data Index: 1933384 (The Pile)

Max Activating Token Index: 261

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.8967. Min Range: -1.8967

Max Act: 0.7912. Min Act: -0.0001

Data Index: 554595 (The Pile)

Max Activating Token Index: 979

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.8967. Min Range: -1.8967

Max Act: 0.7541. Min Act: -0.0001

Data Index: 1942157 (The Pile)

Max Activating Token Index: 394

Click toggle to see full text

Truncated

Full Text #19