< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 23 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0291. Min Act: -0.0002

Data Index: 1847621 (The Pile)

Max Activating Token Index: 931

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0174. Min Act: -0.0002

Data Index: 1071246 (The Pile)

Max Activating Token Index: 957

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0158. Min Act: -0.0003

Data Index: 1326077 (The Pile)

Max Activating Token Index: 984

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0139. Min Act: -0.0003

Data Index: 1463836 (The Pile)

Max Activating Token Index: 1022

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0137. Min Act: -0.0003

Data Index: 686632 (The Pile)

Max Activating Token Index: 924

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0138. Min Act: -0.0003

Data Index: 991663 (The Pile)

Max Activating Token Index: 990

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0129. Min Act: -0.0003

Data Index: 123232 (The Pile)

Max Activating Token Index: 942

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0127. Min Act: -0.0002

Data Index: 326602 (The Pile)

Max Activating Token Index: 968

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0126. Min Act: -0.0003

Data Index: 1068845 (The Pile)

Max Activating Token Index: 971

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0122. Min Act: -0.0003

Data Index: 1433770 (The Pile)

Max Activating Token Index: 944

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0119. Min Act: -0.0003

Data Index: 1471632 (The Pile)

Max Activating Token Index: 995

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0122. Min Act: -0.0002

Data Index: 225952 (The Pile)

Max Activating Token Index: 876

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0125. Min Act: -0.0003

Data Index: 1612354 (The Pile)

Max Activating Token Index: 1012

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0117. Min Act: -0.0002

Data Index: 904059 (The Pile)

Max Activating Token Index: 1021

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0128. Min Act: -0.0003

Data Index: 1635277 (The Pile)

Max Activating Token Index: 989

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0120. Min Act: -0.0003

Data Index: 1584279 (The Pile)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0118. Min Act: -0.0003

Data Index: 1663843 (The Pile)

Max Activating Token Index: 1007

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0131. Min Act: -0.0003

Data Index: 854801 (The Pile)

Max Activating Token Index: 1002

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0122. Min Act: -0.0003

Data Index: 570862 (The Pile)

Max Activating Token Index: 958

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0121. Min Act: -0.0003

Data Index: 134864 (The Pile)

Max Activating Token Index: 1013

Click toggle to see full text

Truncated

Full Text #19