< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 3004 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 2.2666. Min Range: -2.2666

Max Act: 2.2666. Min Act: -0.0001

Data Index: 1165185 (The Pile)

Max Activating Token Index: 142

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.2666. Min Range: -2.2666

Max Act: 2.0962. Min Act: -0.0001

Data Index: 1814826 (The Pile)

Max Activating Token Index: 979

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.2666. Min Range: -2.2666

Max Act: 2.1044. Min Act: -0.0001

Data Index: 1802999 (The Pile)

Max Activating Token Index: 811

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.2666. Min Range: -2.2666

Max Act: 2.0168. Min Act: -0.0001

Data Index: 616251 (The Pile)

Max Activating Token Index: 609

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.2666. Min Range: -2.2666

Max Act: 2.0115. Min Act: -0.0001

Data Index: 1718124 (The Pile)

Max Activating Token Index: 586

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.2666. Min Range: -2.2666

Max Act: 1.9104. Min Act: -0.0001

Data Index: 1973320 (The Pile)

Max Activating Token Index: 929

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.2666. Min Range: -2.2666

Max Act: 2.0613. Min Act: -0.0001

Data Index: 1381264 (The Pile)

Max Activating Token Index: 972

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.2666. Min Range: -2.2666

Max Act: 1.9487. Min Act: -0.0001

Data Index: 777220 (The Pile)

Max Activating Token Index: 425

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.2666. Min Range: -2.2666

Max Act: 1.9262. Min Act: -0.0001

Data Index: 1669806 (The Pile)

Max Activating Token Index: 750

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.2666. Min Range: -2.2666

Max Act: 1.9215. Min Act: -0.0001

Data Index: 1159609 (The Pile)

Max Activating Token Index: 360

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.2666. Min Range: -2.2666

Max Act: 1.7774. Min Act: -0.0001

Data Index: 131176 (The Pile)

Max Activating Token Index: 848

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.2666. Min Range: -2.2666

Max Act: 1.9165. Min Act: -0.0001

Data Index: 566302 (The Pile)

Max Activating Token Index: 835

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.2666. Min Range: -2.2666

Max Act: 1.9110. Min Act: -0.0001

Data Index: 1770582 (The Pile)

Max Activating Token Index: 303

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.2666. Min Range: -2.2666

Max Act: 1.9054. Min Act: -0.0001

Data Index: 1910989 (The Pile)

Max Activating Token Index: 1014

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.2666. Min Range: -2.2666

Max Act: 1.8778. Min Act: -0.0001

Data Index: 1083651 (The Pile)

Max Activating Token Index: 933

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.2666. Min Range: -2.2666

Max Act: 1.7013. Min Act: -0.0001

Data Index: 248345 (The Pile)

Max Activating Token Index: 879

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.2666. Min Range: -2.2666

Max Act: 1.7791. Min Act: -0.0001

Data Index: 588608 (The Pile)

Max Activating Token Index: 817

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.2666. Min Range: -2.2666

Max Act: 1.8422. Min Act: -0.0001

Data Index: 1209338 (The Pile)

Max Activating Token Index: 949

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.2666. Min Range: -2.2666

Max Act: 1.7193. Min Act: -0.0001

Data Index: 104031 (The Pile)

Max Activating Token Index: 277

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.2666. Min Range: -2.2666

Max Act: 1.8319. Min Act: -0.0001

Data Index: 1281912 (The Pile)

Max Activating Token Index: 797

Click toggle to see full text

Truncated

Full Text #19