< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 5112 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 2.4914. Min Range: -2.4914

Max Act: 2.4914. Min Act: -0.0000

Data Index: 888007 (The Pile)

Max Activating Token Index: 184

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.4914. Min Range: -2.4914

Max Act: 2.4441. Min Act: -0.0000

Data Index: 305603 (The Pile)

Max Activating Token Index: 523

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.4914. Min Range: -2.4914

Max Act: 2.1662. Min Act: -0.0000

Data Index: 407055 (The Pile)

Max Activating Token Index: 694

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.4914. Min Range: -2.4914

Max Act: 2.2703. Min Act: -0.0000

Data Index: 505064 (The Pile)

Max Activating Token Index: 478

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.4914. Min Range: -2.4914

Max Act: 2.2492. Min Act: -0.0000

Data Index: 1858593 (The Pile)

Max Activating Token Index: 46

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.4914. Min Range: -2.4914

Max Act: 2.2355. Min Act: -0.0000

Data Index: 1482185 (The Pile)

Max Activating Token Index: 602

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.4914. Min Range: -2.4914

Max Act: 2.1113. Min Act: -0.0000

Data Index: 679572 (The Pile)

Max Activating Token Index: 1017

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.4914. Min Range: -2.4914

Max Act: 2.0729. Min Act: -0.0000

Data Index: 1127362 (The Pile)

Max Activating Token Index: 415

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.4914. Min Range: -2.4914

Max Act: 2.0866. Min Act: -0.0000

Data Index: 1710369 (The Pile)

Max Activating Token Index: 927

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.4914. Min Range: -2.4914

Max Act: 2.1476. Min Act: -0.0000

Data Index: 1080783 (The Pile)

Max Activating Token Index: 96

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.4914. Min Range: -2.4914

Max Act: 2.1294. Min Act: -0.0000

Data Index: 1495450 (The Pile)

Max Activating Token Index: 505

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.4914. Min Range: -2.4914

Max Act: 2.1023. Min Act: -0.0000

Data Index: 164480 (The Pile)

Max Activating Token Index: 263

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.4914. Min Range: -2.4914

Max Act: 1.9688. Min Act: -0.0000

Data Index: 1930514 (The Pile)

Max Activating Token Index: 526

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.4914. Min Range: -2.4914

Max Act: 1.9305. Min Act: -0.0000

Data Index: 1626641 (The Pile)

Max Activating Token Index: 796

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.4914. Min Range: -2.4914

Max Act: 1.9858. Min Act: -0.0000

Data Index: 750516 (The Pile)

Max Activating Token Index: 728

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.4914. Min Range: -2.4914

Max Act: 1.9426. Min Act: -0.0000

Data Index: 1461738 (The Pile)

Max Activating Token Index: 627

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.4914. Min Range: -2.4914

Max Act: 2.0326. Min Act: -0.0000

Data Index: 776612 (The Pile)

Max Activating Token Index: 959

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.4914. Min Range: -2.4914

Max Act: 1.8076. Min Act: -0.0000

Data Index: 1139728 (The Pile)

Max Activating Token Index: 506

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.4914. Min Range: -2.4914

Max Act: 2.0797. Min Act: -0.0000

Data Index: 1193447 (The Pile)

Max Activating Token Index: 572

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.4914. Min Range: -2.4914

Max Act: 1.8621. Min Act: -0.0000

Data Index: 186413 (The Pile)

Max Activating Token Index: 214

Click toggle to see full text

Truncated

Full Text #19