< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 4033 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: 0.0216. Min Range: -0.0216

Max Act: 0.0216. Min Act: -0.0001

Data Index: 1195115 (The Pile)

Max Activating Token Index: 1015

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0195. Min Act: -0.0001

Data Index: 578956 (The Pile)

Max Activating Token Index: 1000

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0186. Min Act: -0.0001

Data Index: 233192 (The Pile)

Max Activating Token Index: 1007

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0180. Min Act: -0.0001

Data Index: 520535 (The Pile)

Max Activating Token Index: 1011

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0176. Min Act: -0.0001

Data Index: 1565928 (The Pile)

Max Activating Token Index: 1021

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0174. Min Act: -0.0001

Data Index: 1907515 (The Pile)

Max Activating Token Index: 1007

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0166. Min Act: -0.0001

Data Index: 1404915 (The Pile)

Max Activating Token Index: 998

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0170. Min Act: -0.0001

Data Index: 969371 (The Pile)

Max Activating Token Index: 1008

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0165. Min Act: -0.0001

Data Index: 573560 (The Pile)

Max Activating Token Index: 987

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0160. Min Act: -0.0001

Data Index: 1092753 (The Pile)

Max Activating Token Index: 1007

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0158. Min Act: -0.0001

Data Index: 623018 (The Pile)

Max Activating Token Index: 1006

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0158. Min Act: -0.0001

Data Index: 1907093 (The Pile)

Max Activating Token Index: 1012

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0156. Min Act: -0.0001

Data Index: 1443652 (The Pile)

Max Activating Token Index: 1002

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0155. Min Act: -0.0001

Data Index: 990330 (The Pile)

Max Activating Token Index: 998

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0153. Min Act: -0.0001

Data Index: 1457261 (The Pile)

Max Activating Token Index: 975

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0151. Min Act: -0.0001

Data Index: 896979 (The Pile)

Max Activating Token Index: 1013

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0141. Min Act: -0.0001

Data Index: 1226465 (The Pile)

Max Activating Token Index: 1005

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0144. Min Act: -0.0001

Data Index: 85396 (The Pile)

Max Activating Token Index: 984

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0143. Min Act: -0.0001

Data Index: 55803 (The Pile)

Max Activating Token Index: 994

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0141. Min Act: -0.0001

Data Index: 512736 (The Pile)

Max Activating Token Index: 1014

Click toggle to see full text

Truncated

Full Text #19