< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 204 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: 3.2068. Min Range: -3.2068

Max Act: 3.2068. Min Act: -0.0000

Data Index: 248480 (The Pile)

Max Activating Token Index: 757

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.2068. Min Range: -3.2068

Max Act: 3.0073. Min Act: 0.0000

Data Index: 1427009 (The Pile)

Max Activating Token Index: 28

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.2068. Min Range: -3.2068

Max Act: 2.3790. Min Act: -0.0000

Data Index: 12218 (The Pile)

Max Activating Token Index: 234

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.2068. Min Range: -3.2068

Max Act: 2.1694. Min Act: 0.0000

Data Index: 1095189 (The Pile)

Max Activating Token Index: 459

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.2068. Min Range: -3.2068

Max Act: 2.1330. Min Act: -0.0000

Data Index: 691309 (The Pile)

Max Activating Token Index: 595

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.2068. Min Range: -3.2068

Max Act: 2.0887. Min Act: -0.0000

Data Index: 932050 (The Pile)

Max Activating Token Index: 262

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.2068. Min Range: -3.2068

Max Act: 1.9802. Min Act: -0.0000

Data Index: 71685 (The Pile)

Max Activating Token Index: 296

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.2068. Min Range: -3.2068

Max Act: 2.1555. Min Act: 0.0000

Data Index: 333070 (The Pile)

Max Activating Token Index: 19

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.2068. Min Range: -3.2068

Max Act: 1.9600. Min Act: -0.0000

Data Index: 760064 (The Pile)

Max Activating Token Index: 734

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.2068. Min Range: -3.2068

Max Act: 1.8349. Min Act: -0.0000

Data Index: 1343361 (The Pile)

Max Activating Token Index: 237

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.2068. Min Range: -3.2068

Max Act: 1.9324. Min Act: -0.0000

Data Index: 504199 (The Pile)

Max Activating Token Index: 364

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.2068. Min Range: -3.2068

Max Act: 1.6112. Min Act: -0.0000

Data Index: 328352 (The Pile)

Max Activating Token Index: 941

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.2068. Min Range: -3.2068

Max Act: 1.8247. Min Act: -0.0000

Data Index: 513077 (The Pile)

Max Activating Token Index: 978

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.2068. Min Range: -3.2068

Max Act: 1.8161. Min Act: -0.0000

Data Index: 837983 (The Pile)

Max Activating Token Index: 379

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.2068. Min Range: -3.2068

Max Act: 1.6301. Min Act: -0.0000

Data Index: 1682298 (The Pile)

Max Activating Token Index: 459

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.2068. Min Range: -3.2068

Max Act: 1.6115. Min Act: -0.0000

Data Index: 933087 (The Pile)

Max Activating Token Index: 195

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.2068. Min Range: -3.2068

Max Act: 2.0417. Min Act: 0.0000

Data Index: 108729 (The Pile)

Max Activating Token Index: 30

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.2068. Min Range: -3.2068

Max Act: 1.7852. Min Act: -0.0000

Data Index: 1368765 (The Pile)

Max Activating Token Index: 410

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.2068. Min Range: -3.2068

Max Act: 1.6659. Min Act: -0.0000

Data Index: 1238303 (The Pile)

Max Activating Token Index: 271

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.2068. Min Range: -3.2068

Max Act: 1.5394. Min Act: -0.0000

Data Index: 1897314 (The Pile)

Max Activating Token Index: 702

Click toggle to see full text

Truncated

Full Text #19