< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 1991 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')



Text #0

Max Range: 9.4843. Min Range: -9.4843

Max Act: 9.1718. Min Act: -0.1699

Data Index: 1425972 (The Pile)

Max Activating Token Index: 156

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 9.4843. Min Range: -9.4843

Max Act: 9.0468. Min Act: -0.1699

Data Index: 2146453 (The Pile)

Max Activating Token Index: 91

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 9.4843. Min Range: -9.4843

Max Act: 8.9843. Min Act: -0.1699

Data Index: 464314 (The Pile)

Max Activating Token Index: 623

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 9.4843. Min Range: -9.4843

Max Act: 9.4843. Min Act: -0.1699

Data Index: 2249804 (The Pile)

Max Activating Token Index: 699

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 9.4843. Min Range: -9.4843

Max Act: 9.2968. Min Act: -0.1699

Data Index: 9636951 (The Pile)

Max Activating Token Index: 974

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 9.4843. Min Range: -9.4843

Max Act: 9.3906. Min Act: -0.1699

Data Index: 8507081 (The Pile)

Max Activating Token Index: 64

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 9.4843. Min Range: -9.4843

Max Act: 9.3906. Min Act: -0.1699

Data Index: 1787713 (The Pile)

Max Activating Token Index: 252

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 9.4843. Min Range: -9.4843

Max Act: 8.9531. Min Act: -0.1699

Data Index: 8372935 (The Pile)

Max Activating Token Index: 715

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 9.4843. Min Range: -9.4843

Max Act: 9.1718. Min Act: -0.1699

Data Index: 7403136 (The Pile)

Max Activating Token Index: 20

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 9.4843. Min Range: -9.4843

Max Act: 9.3906. Min Act: -0.1699

Data Index: 5547187 (The Pile)

Max Activating Token Index: 161

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 9.4843. Min Range: -9.4843

Max Act: 8.8281. Min Act: -0.1699

Data Index: 2797078 (The Pile)

Max Activating Token Index: 49

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 9.4843. Min Range: -9.4843

Max Act: 9.0468. Min Act: -0.1699

Data Index: 1632269 (The Pile)

Max Activating Token Index: 644

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 9.4843. Min Range: -9.4843

Max Act: 9.4843. Min Act: -0.1699

Data Index: 6340885 (The Pile)

Max Activating Token Index: 96

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 9.4843. Min Range: -9.4843

Max Act: 9.2968. Min Act: -0.1699

Data Index: 3413520 (The Pile)

Max Activating Token Index: 673

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 9.4843. Min Range: -9.4843

Max Act: 9.2968. Min Act: -0.1699

Data Index: 9422292 (The Pile)

Max Activating Token Index: 936

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 9.4843. Min Range: -9.4843

Max Act: 8.9218. Min Act: -0.1699

Data Index: 8492044 (The Pile)

Max Activating Token Index: 37

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 9.4843. Min Range: -9.4843

Max Act: 9.1406. Min Act: -0.1699

Data Index: 5034157 (The Pile)

Max Activating Token Index: 78

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 9.4843. Min Range: -9.4843

Max Act: 9.0156. Min Act: -0.1699

Data Index: 563746 (The Pile)

Max Activating Token Index: 199

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 9.4843. Min Range: -9.4843

Max Act: 9.1718. Min Act: -0.1699

Data Index: 460292 (The Pile)

Max Activating Token Index: 395

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 9.4843. Min Range: -9.4843

Max Act: 9.1093. Min Act: -0.1699

Data Index: 1294206 (The Pile)

Max Activating Token Index: 878

Click toggle to see full text

Truncated

Full Text #19