< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 144 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1416. Min Act: 0.0000

Data Index: 147467 (The Pile)

Max Activating Token Index: 457

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1404. Min Act: -0.0000

Data Index: 1136307 (The Pile)

Max Activating Token Index: 846

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1257. Min Act: -0.0000

Data Index: 1933136 (The Pile)

Max Activating Token Index: 580

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1287. Min Act: -0.0000

Data Index: 1196242 (The Pile)

Max Activating Token Index: 186

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1255. Min Act: -0.0000

Data Index: 1220047 (The Pile)

Max Activating Token Index: 243

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1265. Min Act: -0.0000

Data Index: 1755622 (The Pile)

Max Activating Token Index: 112

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1201. Min Act: -0.0000

Data Index: 1267065 (The Pile)

Max Activating Token Index: 215

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1127. Min Act: -0.0000

Data Index: 1154831 (The Pile)

Max Activating Token Index: 55

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1173. Min Act: -0.0000

Data Index: 1055493 (The Pile)

Max Activating Token Index: 399

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1176. Min Act: -0.0000

Data Index: 1743635 (The Pile)

Max Activating Token Index: 222

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1144. Min Act: -0.0000

Data Index: 914928 (The Pile)

Max Activating Token Index: 944

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1127. Min Act: -0.0000

Data Index: 368495 (The Pile)

Max Activating Token Index: 261

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1047. Min Act: -0.0000

Data Index: 199268 (The Pile)

Max Activating Token Index: 695

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1079. Min Act: -0.0000

Data Index: 203716 (The Pile)

Max Activating Token Index: 252

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1062. Min Act: -0.0000

Data Index: 1394362 (The Pile)

Max Activating Token Index: 183

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.0992. Min Act: -0.0000

Data Index: 655099 (The Pile)

Max Activating Token Index: 105

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1129. Min Act: -0.0000

Data Index: 1096811 (The Pile)

Max Activating Token Index: 279

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1116. Min Act: -0.0000

Data Index: 1074048 (The Pile)

Max Activating Token Index: 789

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.0823. Min Act: -0.0000

Data Index: 1924404 (The Pile)

Max Activating Token Index: 702

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1094. Min Act: -0.0000

Data Index: 1416400 (The Pile)

Max Activating Token Index: 84

Click toggle to see full text

Truncated

Full Text #19