< Prev | Home | Model | Random | Next >

Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: The Pile

Neuron 2014 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l-pile')



Text #0

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1252. Min Act: 0.0002

Data Index: 1664729 (The Pile)

Max Activating Token Index: 426

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1214. Min Act: 0.0002

Data Index: 1464362 (The Pile)

Max Activating Token Index: 684

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1218. Min Act: 0.0001

Data Index: 30837 (The Pile)

Max Activating Token Index: 570

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1212. Min Act: 0.0001

Data Index: 958384 (The Pile)

Max Activating Token Index: 626

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1244. Min Act: 0.0002

Data Index: 1506941 (The Pile)

Max Activating Token Index: 1019

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1164. Min Act: -0.0001

Data Index: 89116 (The Pile)

Max Activating Token Index: 208

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1139. Min Act: 0.0004

Data Index: 1985477 (The Pile)

Max Activating Token Index: 93

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1134. Min Act: 0.0002

Data Index: 16010 (The Pile)

Max Activating Token Index: 259

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1091. Min Act: 0.0000

Data Index: 552152 (The Pile)

Max Activating Token Index: 450

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1171. Min Act: 0.0000

Data Index: 925069 (The Pile)

Max Activating Token Index: 347

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1122. Min Act: 0.0004

Data Index: 401751 (The Pile)

Max Activating Token Index: 1015

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1101. Min Act: 0.0002

Data Index: 992985 (The Pile)

Max Activating Token Index: 573

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1099. Min Act: 0.0005

Data Index: 1460733 (The Pile)

Max Activating Token Index: 867

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1055. Min Act: 0.0001

Data Index: 1909991 (The Pile)

Max Activating Token Index: 128

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1091. Min Act: 0.0001

Data Index: 731994 (The Pile)

Max Activating Token Index: 72

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1042. Min Act: 0.0003

Data Index: 1678769 (The Pile)

Max Activating Token Index: 495

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1029. Min Act: 0.0000

Data Index: 1810749 (The Pile)

Max Activating Token Index: 638

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1034. Min Act: 0.0002

Data Index: 894653 (The Pile)

Max Activating Token Index: 906

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0992. Min Act: 0.0000

Data Index: 1049461 (The Pile)

Max Activating Token Index: 113

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1058. Min Act: 0.0005

Data Index: 1451161 (The Pile)

Max Activating Token Index: 580

Click toggle to see full text

Truncated

Full Text #19