< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 2395 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.1834. Min Range: -1.1834

Max Act: 1.1834. Min Act: -0.0001

Data Index: 1160841 (The Pile)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.1834. Min Range: -1.1834

Max Act: 1.0115. Min Act: -0.0001

Data Index: 1715519 (The Pile)

Max Activating Token Index: 671

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.1834. Min Range: -1.1834

Max Act: 1.0092. Min Act: -0.0001

Data Index: 1517327 (The Pile)

Max Activating Token Index: 844

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.1834. Min Range: -1.1834

Max Act: 0.9610. Min Act: -0.0001

Data Index: 1473094 (The Pile)

Max Activating Token Index: 912

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.1834. Min Range: -1.1834

Max Act: 0.9518. Min Act: -0.0001

Data Index: 412398 (The Pile)

Max Activating Token Index: 806

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.1834. Min Range: -1.1834

Max Act: 0.9563. Min Act: -0.0001

Data Index: 1817490 (The Pile)

Max Activating Token Index: 936

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.1834. Min Range: -1.1834

Max Act: 0.9471. Min Act: -0.0001

Data Index: 1974031 (The Pile)

Max Activating Token Index: 215

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.1834. Min Range: -1.1834

Max Act: 0.9117. Min Act: -0.0001

Data Index: 1037265 (The Pile)

Max Activating Token Index: 302

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.1834. Min Range: -1.1834

Max Act: 0.9319. Min Act: -0.0001

Data Index: 1498640 (The Pile)

Max Activating Token Index: 545

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.1834. Min Range: -1.1834

Max Act: 0.9314. Min Act: -0.0001

Data Index: 642767 (The Pile)

Max Activating Token Index: 79

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.1834. Min Range: -1.1834

Max Act: 0.9289. Min Act: -0.0001

Data Index: 1784380 (The Pile)

Max Activating Token Index: 495

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.1834. Min Range: -1.1834

Max Act: 0.9263. Min Act: -0.0001

Data Index: 276020 (The Pile)

Max Activating Token Index: 436

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.1834. Min Range: -1.1834

Max Act: 0.9216. Min Act: -0.0001

Data Index: 1952527 (The Pile)

Max Activating Token Index: 330

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.1834. Min Range: -1.1834

Max Act: 0.8967. Min Act: -0.0001

Data Index: 886918 (The Pile)

Max Activating Token Index: 509

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.1834. Min Range: -1.1834

Max Act: 0.9207. Min Act: -0.0001

Data Index: 981813 (The Pile)

Max Activating Token Index: 470

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.1834. Min Range: -1.1834

Max Act: 0.9189. Min Act: -0.0001

Data Index: 1792724 (The Pile)

Max Activating Token Index: 42

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.1834. Min Range: -1.1834

Max Act: 0.9128. Min Act: -0.0001

Data Index: 1689538 (The Pile)

Max Activating Token Index: 191

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.1834. Min Range: -1.1834

Max Act: 0.9047. Min Act: -0.0001

Data Index: 1698995 (The Pile)

Max Activating Token Index: 505

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.1834. Min Range: -1.1834

Max Act: 0.9006. Min Act: -0.0001

Data Index: 1557189 (The Pile)

Max Activating Token Index: 112

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.1834. Min Range: -1.1834

Max Act: 0.9021. Min Act: -0.0001

Data Index: 1152857 (The Pile)

Max Activating Token Index: 451

Click toggle to see full text

Truncated

Full Text #19