< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 5114 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: 6.3766. Min Range: -6.3766

Max Act: 6.3766. Min Act: -0.0000

Data Index: 1827102 (The Pile)

Max Activating Token Index: 17

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 6.3766. Min Range: -6.3766

Max Act: 6.2898. Min Act: -0.0000

Data Index: 1765197 (The Pile)

Max Activating Token Index: 1022

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 6.3766. Min Range: -6.3766

Max Act: 6.3061. Min Act: -0.0000

Data Index: 443529 (The Pile)

Max Activating Token Index: 12

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 6.3766. Min Range: -6.3766

Max Act: 6.2674. Min Act: -0.0000

Data Index: 538565 (The Pile)

Max Activating Token Index: 14

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 6.3766. Min Range: -6.3766

Max Act: 6.3584. Min Act: -0.0000

Data Index: 1967667 (The Pile)

Max Activating Token Index: 11

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 6.3766. Min Range: -6.3766

Max Act: 6.0772. Min Act: -0.0000

Data Index: 643039 (The Pile)

Max Activating Token Index: 12

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 6.3766. Min Range: -6.3766

Max Act: 6.0554. Min Act: -0.0000

Data Index: 541654 (The Pile)

Max Activating Token Index: 14

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 6.3766. Min Range: -6.3766

Max Act: 6.0753. Min Act: -0.0000

Data Index: 293664 (The Pile)

Max Activating Token Index: 633

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 6.3766. Min Range: -6.3766

Max Act: 5.9012. Min Act: -0.0000

Data Index: 1959254 (The Pile)

Max Activating Token Index: 10

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 6.3766. Min Range: -6.3766

Max Act: 5.9208. Min Act: -0.0000

Data Index: 821087 (The Pile)

Max Activating Token Index: 13

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 6.3766. Min Range: -6.3766

Max Act: 5.8869. Min Act: -0.0000

Data Index: 1327641 (The Pile)

Max Activating Token Index: 162

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 6.3766. Min Range: -6.3766

Max Act: 5.8976. Min Act: -0.0000

Data Index: 77460 (The Pile)

Max Activating Token Index: 93

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 6.3766. Min Range: -6.3766

Max Act: 5.6282. Min Act: -0.0000

Data Index: 1850302 (The Pile)

Max Activating Token Index: 406

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 6.3766. Min Range: -6.3766

Max Act: 5.5617. Min Act: -0.0000

Data Index: 704791 (The Pile)

Max Activating Token Index: 740

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 6.3766. Min Range: -6.3766

Max Act: 5.9058. Min Act: -0.0000

Data Index: 1906883 (The Pile)

Max Activating Token Index: 176

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 6.3766. Min Range: -6.3766

Max Act: 5.8588. Min Act: -0.0000

Data Index: 559969 (The Pile)

Max Activating Token Index: 16

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 6.3766. Min Range: -6.3766

Max Act: 5.3341. Min Act: -0.0000

Data Index: 628521 (The Pile)

Max Activating Token Index: 13

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 6.3766. Min Range: -6.3766

Max Act: 5.6787. Min Act: -0.0000

Data Index: 660001 (The Pile)

Max Activating Token Index: 12

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 6.3766. Min Range: -6.3766

Max Act: 5.6376. Min Act: -0.0000

Data Index: 1376476 (The Pile)

Max Activating Token Index: 11

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 6.3766. Min Range: -6.3766

Max Act: 5.7920. Min Act: -0.0000

Data Index: 1962887 (The Pile)

Max Activating Token Index: 12

Click toggle to see full text

Truncated

Full Text #19