< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 4063 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.6855. Min Range: -0.6855

Max Act: 0.6410. Min Act: -0.0001

Data Index: 1860971 (The Pile)

Max Activating Token Index: 78

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.6855. Min Range: -0.6855

Max Act: 0.6855. Min Act: -0.0001

Data Index: 1167592 (The Pile)

Max Activating Token Index: 183

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.6855. Min Range: -0.6855

Max Act: 0.6643. Min Act: -0.0001

Data Index: 388201 (The Pile)

Max Activating Token Index: 750

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.6855. Min Range: -0.6855

Max Act: 0.5964. Min Act: -0.0002

Data Index: 1132319 (The Pile)

Max Activating Token Index: 59

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.6855. Min Range: -0.6855

Max Act: 0.5913. Min Act: -0.0001

Data Index: 578766 (The Pile)

Max Activating Token Index: 169

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.6855. Min Range: -0.6855

Max Act: 0.6101. Min Act: -0.0001

Data Index: 1778421 (The Pile)

Max Activating Token Index: 782

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.6855. Min Range: -0.6855

Max Act: 0.5752. Min Act: -0.0001

Data Index: 899189 (The Pile)

Max Activating Token Index: 590

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.6855. Min Range: -0.6855

Max Act: 0.5014. Min Act: -0.0001

Data Index: 1970346 (The Pile)

Max Activating Token Index: 416

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.6855. Min Range: -0.6855

Max Act: 0.5341. Min Act: -0.0001

Data Index: 803675 (The Pile)

Max Activating Token Index: 318

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.6855. Min Range: -0.6855

Max Act: 0.5631. Min Act: -0.0001

Data Index: 1509492 (The Pile)

Max Activating Token Index: 146

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.6855. Min Range: -0.6855

Max Act: 0.5623. Min Act: -0.0001

Data Index: 483345 (The Pile)

Max Activating Token Index: 220

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.6855. Min Range: -0.6855

Max Act: 0.5437. Min Act: -0.0001

Data Index: 1927967 (The Pile)

Max Activating Token Index: 562

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.6855. Min Range: -0.6855

Max Act: 0.5951. Min Act: -0.0001

Data Index: 10667 (The Pile)

Max Activating Token Index: 915

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.6855. Min Range: -0.6855

Max Act: 0.5804. Min Act: -0.0001

Data Index: 1392940 (The Pile)

Max Activating Token Index: 52

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.6855. Min Range: -0.6855

Max Act: 0.5355. Min Act: -0.0001

Data Index: 1260254 (The Pile)

Max Activating Token Index: 172

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.6855. Min Range: -0.6855

Max Act: 0.5708. Min Act: -0.0001

Data Index: 673649 (The Pile)

Max Activating Token Index: 276

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.6855. Min Range: -0.6855

Max Act: 0.6033. Min Act: -0.0001

Data Index: 627031 (The Pile)

Max Activating Token Index: 929

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.6855. Min Range: -0.6855

Max Act: 0.4941. Min Act: -0.0001

Data Index: 1803196 (The Pile)

Max Activating Token Index: 888

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.6855. Min Range: -0.6855

Max Act: 0.5765. Min Act: -0.0001

Data Index: 1974113 (The Pile)

Max Activating Token Index: 725

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.6855. Min Range: -0.6855

Max Act: 0.5625. Min Act: -0.0001

Data Index: 1590209 (The Pile)

Max Activating Token Index: 260

Click toggle to see full text

Truncated

Full Text #19