< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 4090 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.5838. Min Range: -1.5838

Max Act: 1.5838. Min Act: 0.0000

Data Index: 1953624 (The Pile)

Max Activating Token Index: 101

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.5838. Min Range: -1.5838

Max Act: 1.5790. Min Act: -0.0000

Data Index: 1716451 (The Pile)

Max Activating Token Index: 551

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.5838. Min Range: -1.5838

Max Act: 1.5790. Min Act: 0.0000

Data Index: 1852316 (The Pile)

Max Activating Token Index: 240

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.5838. Min Range: -1.5838

Max Act: 1.5679. Min Act: 0.0000

Data Index: 1908514 (The Pile)

Max Activating Token Index: 496

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.5838. Min Range: -1.5838

Max Act: 1.3132. Min Act: 0.0000

Data Index: 120108 (The Pile)

Max Activating Token Index: 245

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.5838. Min Range: -1.5838

Max Act: 1.4220. Min Act: 0.0000

Data Index: 1224887 (The Pile)

Max Activating Token Index: 289

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.5838. Min Range: -1.5838

Max Act: 1.4870. Min Act: -0.0000

Data Index: 619098 (The Pile)

Max Activating Token Index: 1017

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.5838. Min Range: -1.5838

Max Act: 1.4207. Min Act: 0.0000

Data Index: 1593522 (The Pile)

Max Activating Token Index: 22

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.5838. Min Range: -1.5838

Max Act: 1.4786. Min Act: 0.0000

Data Index: 1617787 (The Pile)

Max Activating Token Index: 183

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.5838. Min Range: -1.5838

Max Act: 1.4618. Min Act: 0.0000

Data Index: 1797788 (The Pile)

Max Activating Token Index: 184

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.5838. Min Range: -1.5838

Max Act: 1.4471. Min Act: 0.0000

Data Index: 806237 (The Pile)

Max Activating Token Index: 844

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.5838. Min Range: -1.5838

Max Act: 1.3575. Min Act: 0.0000

Data Index: 509662 (The Pile)

Max Activating Token Index: 47

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.5838. Min Range: -1.5838

Max Act: 1.3571. Min Act: 0.0000

Data Index: 1014395 (The Pile)

Max Activating Token Index: 470

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.5838. Min Range: -1.5838

Max Act: 1.3351. Min Act: 0.0000

Data Index: 1340400 (The Pile)

Max Activating Token Index: 386

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.5838. Min Range: -1.5838

Max Act: 1.2672. Min Act: -0.0000

Data Index: 7761 (The Pile)

Max Activating Token Index: 595

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.5838. Min Range: -1.5838

Max Act: 1.1117. Min Act: -0.0000

Data Index: 981680 (The Pile)

Max Activating Token Index: 716

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.5838. Min Range: -1.5838

Max Act: 1.3041. Min Act: 0.0001

Data Index: 1982332 (The Pile)

Max Activating Token Index: 678

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.5838. Min Range: -1.5838

Max Act: 1.2196. Min Act: -0.0000

Data Index: 118577 (The Pile)

Max Activating Token Index: 287

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.5838. Min Range: -1.5838

Max Act: 1.2933. Min Act: -0.0000

Data Index: 355909 (The Pile)

Max Activating Token Index: 967

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.5838. Min Range: -1.5838

Max Act: 1.2830. Min Act: -0.0000

Data Index: 1750265 (The Pile)

Max Activating Token Index: 773

Click toggle to see full text

Truncated

Full Text #19