< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 18 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.8523. Min Act: -0.0001

Data Index: 1551688 (The Pile)

Max Activating Token Index: 1001

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.8613. Min Act: -0.0001

Data Index: 1127349 (The Pile)

Max Activating Token Index: 243

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.8438. Min Act: -0.0001

Data Index: 608448 (The Pile)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.8009. Min Act: -0.0001

Data Index: 1967772 (The Pile)

Max Activating Token Index: 332

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.7664. Min Act: -0.0001

Data Index: 206013 (The Pile)

Max Activating Token Index: 520

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.7300. Min Act: -0.0001

Data Index: 717405 (The Pile)

Max Activating Token Index: 938

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.7075. Min Act: -0.0001

Data Index: 873159 (The Pile)

Max Activating Token Index: 149

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.7246. Min Act: -0.0001

Data Index: 1896756 (The Pile)

Max Activating Token Index: 653

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.7138. Min Act: -0.0001

Data Index: 302412 (The Pile)

Max Activating Token Index: 790

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.7153. Min Act: -0.0001

Data Index: 400684 (The Pile)

Max Activating Token Index: 128

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.7569. Min Act: -0.0001

Data Index: 883583 (The Pile)

Max Activating Token Index: 370

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.6774. Min Act: -0.0001

Data Index: 1058290 (The Pile)

Max Activating Token Index: 720

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.7199. Min Act: -0.0001

Data Index: 443193 (The Pile)

Max Activating Token Index: 8

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.6954. Min Act: -0.0001

Data Index: 363783 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.6911. Min Act: -0.0001

Data Index: 1113932 (The Pile)

Max Activating Token Index: 94

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.6489. Min Act: -0.0001

Data Index: 1478327 (The Pile)

Max Activating Token Index: 812

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.7338. Min Act: -0.0001

Data Index: 97788 (The Pile)

Max Activating Token Index: 785

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.6662. Min Act: -0.0001

Data Index: 1318963 (The Pile)

Max Activating Token Index: 423

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.6433. Min Act: -0.0001

Data Index: 1758639 (The Pile)

Max Activating Token Index: 101

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.6484. Min Act: -0.0001

Data Index: 10926 (The Pile)

Max Activating Token Index: 10

Click toggle to see full text

Truncated

Full Text #19