< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 4054 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0056. Min Act: -0.0001

Data Index: 804386 (The Pile)

Max Activating Token Index: 1021

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0056. Min Act: -0.0001

Data Index: 1892120 (The Pile)

Max Activating Token Index: 1017

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0056. Min Act: -0.0001

Data Index: 1744531 (The Pile)

Max Activating Token Index: 1019

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0054. Min Act: -0.0001

Data Index: 1263261 (The Pile)

Max Activating Token Index: 1020

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0054. Min Act: -0.0001

Data Index: 953209 (The Pile)

Max Activating Token Index: 1020

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0054. Min Act: -0.0001

Data Index: 1983474 (The Pile)

Max Activating Token Index: 1019

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0054. Min Act: -0.0001

Data Index: 19813 (The Pile)

Max Activating Token Index: 1019

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0053. Min Act: -0.0001

Data Index: 668188 (The Pile)

Max Activating Token Index: 1013

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0053. Min Act: -0.0001

Data Index: 1253083 (The Pile)

Max Activating Token Index: 1019

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0052. Min Act: -0.0001

Data Index: 1750577 (The Pile)

Max Activating Token Index: 1019

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0054. Min Act: -0.0001

Data Index: 1909437 (The Pile)

Max Activating Token Index: 1019

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0052. Min Act: -0.0001

Data Index: 623358 (The Pile)

Max Activating Token Index: 1019

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0052. Min Act: -0.0001

Data Index: 1611142 (The Pile)

Max Activating Token Index: 1022

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0052. Min Act: -0.0001

Data Index: 662450 (The Pile)

Max Activating Token Index: 1019

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0051. Min Act: -0.0001

Data Index: 1484555 (The Pile)

Max Activating Token Index: 1020

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0051. Min Act: -0.0001

Data Index: 958520 (The Pile)

Max Activating Token Index: 1021

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0051. Min Act: -0.0001

Data Index: 1968717 (The Pile)

Max Activating Token Index: 1018

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0051. Min Act: -0.0001

Data Index: 1872943 (The Pile)

Max Activating Token Index: 1021

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0052. Min Act: -0.0001

Data Index: 1512540 (The Pile)

Max Activating Token Index: 1020

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0052. Min Act: -0.0001

Data Index: 1499396 (The Pile)

Max Activating Token Index: 1021

Click toggle to see full text

Truncated

Full Text #19