< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 40 in Layer 20

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')



Text #0

Max Range: 10.2080. Min Range: -10.2080

Max Act: 10.2080. Min Act: -0.1700

Data Index: 3332844 (The Pile)

Max Activating Token Index: 505

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 10.2080. Min Range: -10.2080

Max Act: 10.0205. Min Act: -0.1700

Data Index: 1379250 (The Pile)

Max Activating Token Index: 260

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 10.2080. Min Range: -10.2080

Max Act: 9.8955. Min Act: -0.1700

Data Index: 3929066 (The Pile)

Max Activating Token Index: 214

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 10.2080. Min Range: -10.2080

Max Act: 9.7705. Min Act: -0.1700

Data Index: 3645483 (The Pile)

Max Activating Token Index: 393

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 10.2080. Min Range: -10.2080

Max Act: 9.5830. Min Act: -0.1697

Data Index: 5954065 (The Pile)

Max Activating Token Index: 578

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 10.2080. Min Range: -10.2080

Max Act: 9.3955. Min Act: -0.1700

Data Index: 5393115 (The Pile)

Max Activating Token Index: 565

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 10.2080. Min Range: -10.2080

Max Act: 9.3955. Min Act: -0.1700

Data Index: 3901235 (The Pile)

Max Activating Token Index: 219

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 10.2080. Min Range: -10.2080

Max Act: 9.3955. Min Act: -0.1700

Data Index: 6564081 (The Pile)

Max Activating Token Index: 743

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 10.2080. Min Range: -10.2080

Max Act: 9.3955. Min Act: -0.1699

Data Index: 10128615 (The Pile)

Max Activating Token Index: 728

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 10.2080. Min Range: -10.2080

Max Act: 9.3330. Min Act: -0.1699

Data Index: 6209783 (The Pile)

Max Activating Token Index: 486

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 10.2080. Min Range: -10.2080

Max Act: 9.2705. Min Act: -0.1700

Data Index: 2662263 (The Pile)

Max Activating Token Index: 331

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 10.2080. Min Range: -10.2080

Max Act: 9.2080. Min Act: -0.1700

Data Index: 5374392 (The Pile)

Max Activating Token Index: 174

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 10.2080. Min Range: -10.2080

Max Act: 9.2080. Min Act: -0.1700

Data Index: 6339486 (The Pile)

Max Activating Token Index: 153

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 10.2080. Min Range: -10.2080

Max Act: 9.1455. Min Act: -0.1700

Data Index: 3454220 (The Pile)

Max Activating Token Index: 952

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 10.2080. Min Range: -10.2080

Max Act: 9.1455. Min Act: -0.1700

Data Index: 9196316 (The Pile)

Max Activating Token Index: 211

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 10.2080. Min Range: -10.2080

Max Act: 9.1455. Min Act: -0.1700

Data Index: 8490788 (The Pile)

Max Activating Token Index: 914

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 10.2080. Min Range: -10.2080

Max Act: 9.1455. Min Act: -0.1700

Data Index: 1623012 (The Pile)

Max Activating Token Index: 260

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 10.2080. Min Range: -10.2080

Max Act: 9.0830. Min Act: -0.1700

Data Index: 5753547 (The Pile)

Max Activating Token Index: 215

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 10.2080. Min Range: -10.2080

Max Act: 9.0205. Min Act: -0.1700

Data Index: 2785044 (The Pile)

Max Activating Token Index: 870

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 10.2080. Min Range: -10.2080

Max Act: 9.0205. Min Act: -0.1700

Data Index: 8414857 (The Pile)

Max Activating Token Index: 169

Click toggle to see full text

Truncated

Full Text #19