< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 4090 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: 0.0100. Min Range: -0.0100

Max Act: 0.0100. Min Act: -0.0001

Data Index: 122338 (The Pile)

Max Activating Token Index: 12

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0097. Min Act: -0.0000

Data Index: 1040368 (The Pile)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0093. Min Act: -0.0001

Data Index: 1899516 (The Pile)

Max Activating Token Index: 19

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0094. Min Act: 0.0000

Data Index: 1118885 (The Pile)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0092. Min Act: -0.0000

Data Index: 486343 (The Pile)

Max Activating Token Index: 28

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0092. Min Act: -0.0001

Data Index: 1663982 (The Pile)

Max Activating Token Index: 14

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0091. Min Act: -0.0001

Data Index: 577573 (The Pile)

Max Activating Token Index: 8

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0089. Min Act: -0.0001

Data Index: 227510 (The Pile)

Max Activating Token Index: 14

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0088. Min Act: -0.0000

Data Index: 524285 (The Pile)

Max Activating Token Index: 57

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0088. Min Act: -0.0000

Data Index: 551254 (The Pile)

Max Activating Token Index: 45

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0087. Min Act: -0.0001

Data Index: 828926 (The Pile)

Max Activating Token Index: 34

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0087. Min Act: -0.0001

Data Index: 1136917 (The Pile)

Max Activating Token Index: 12

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0085. Min Act: -0.0000

Data Index: 339707 (The Pile)

Max Activating Token Index: 16

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0086. Min Act: -0.0001

Data Index: 1039374 (The Pile)

Max Activating Token Index: 14

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0086. Min Act: -0.0000

Data Index: 743313 (The Pile)

Max Activating Token Index: 110

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0087. Min Act: -0.0001

Data Index: 994628 (The Pile)

Max Activating Token Index: 100

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0087. Min Act: -0.0000

Data Index: 1850044 (The Pile)

Max Activating Token Index: 25

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0083. Min Act: -0.0001

Data Index: 643295 (The Pile)

Max Activating Token Index: 9

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0085. Min Act: -0.0001

Data Index: 681055 (The Pile)

Max Activating Token Index: 9

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0084. Min Act: -0.0001

Data Index: 1707142 (The Pile)

Max Activating Token Index: 15

Click toggle to see full text

Truncated

Full Text #19