< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 59 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: 1.4779. Min Range: -1.4779

Max Act: 1.4487. Min Act: -0.0001

Data Index: 648356 (The Pile)

Max Activating Token Index: 337

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.4779. Min Range: -1.4779

Max Act: 1.4779. Min Act: -0.0001

Data Index: 1220427 (The Pile)

Max Activating Token Index: 741

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.4779. Min Range: -1.4779

Max Act: 1.3836. Min Act: -0.0001

Data Index: 1964714 (The Pile)

Max Activating Token Index: 588

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.4779. Min Range: -1.4779

Max Act: 1.3441. Min Act: -0.0000

Data Index: 1915026 (The Pile)

Max Activating Token Index: 217

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.4779. Min Range: -1.4779

Max Act: 1.1628. Min Act: -0.0001

Data Index: 1793794 (The Pile)

Max Activating Token Index: 518

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.4779. Min Range: -1.4779

Max Act: 1.3338. Min Act: -0.0001

Data Index: 1110959 (The Pile)

Max Activating Token Index: 135

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.4779. Min Range: -1.4779

Max Act: 1.0643. Min Act: -0.0001

Data Index: 1846496 (The Pile)

Max Activating Token Index: 696

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.4779. Min Range: -1.4779

Max Act: 1.3390. Min Act: -0.0000

Data Index: 1060250 (The Pile)

Max Activating Token Index: 398

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.4779. Min Range: -1.4779

Max Act: 1.0389. Min Act: -0.0001

Data Index: 1899261 (The Pile)

Max Activating Token Index: 200

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.4779. Min Range: -1.4779

Max Act: 0.9061. Min Act: -0.0001

Data Index: 1371425 (The Pile)

Max Activating Token Index: 690

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.4779. Min Range: -1.4779

Max Act: 1.0662. Min Act: -0.0000

Data Index: 1937408 (The Pile)

Max Activating Token Index: 288

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.4779. Min Range: -1.4779

Max Act: 0.9392. Min Act: -0.0000

Data Index: 1707763 (The Pile)

Max Activating Token Index: 245

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.4779. Min Range: -1.4779

Max Act: 0.9872. Min Act: -0.0001

Data Index: 358684 (The Pile)

Max Activating Token Index: 651

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.4779. Min Range: -1.4779

Max Act: 0.9383. Min Act: -0.0000

Data Index: 1542904 (The Pile)

Max Activating Token Index: 300

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.4779. Min Range: -1.4779

Max Act: 0.9243. Min Act: -0.0001

Data Index: 1135175 (The Pile)

Max Activating Token Index: 552

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.4779. Min Range: -1.4779

Max Act: 0.8147. Min Act: -0.0001

Data Index: 805748 (The Pile)

Max Activating Token Index: 458

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.4779. Min Range: -1.4779

Max Act: 0.9014. Min Act: -0.0001

Data Index: 652392 (The Pile)

Max Activating Token Index: 96

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.4779. Min Range: -1.4779

Max Act: 0.9464. Min Act: -0.0000

Data Index: 1031422 (The Pile)

Max Activating Token Index: 152

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.4779. Min Range: -1.4779

Max Act: 0.8331. Min Act: -0.0001

Data Index: 1877770 (The Pile)

Max Activating Token Index: 181

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.4779. Min Range: -1.4779

Max Act: 0.8709. Min Act: -0.0001

Data Index: 546257 (The Pile)

Max Activating Token Index: 224

Click toggle to see full text

Truncated

Full Text #19