< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 61 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.5361. Min Range: -3.5361

Max Act: 3.5047. Min Act: -0.1700

Data Index: 5659917 (The Pile)

Max Activating Token Index: 370

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.5361. Min Range: -3.5361

Max Act: 3.5361. Min Act: -0.1700

Data Index: 10138102 (The Pile)

Max Activating Token Index: 985

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.5361. Min Range: -3.5361

Max Act: 3.4577. Min Act: -0.1700

Data Index: 919544 (The Pile)

Max Activating Token Index: 271

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.5361. Min Range: -3.5361

Max Act: 3.4264. Min Act: -0.1700

Data Index: 10573631 (The Pile)

Max Activating Token Index: 174

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.5361. Min Range: -3.5361

Max Act: 3.4421. Min Act: -0.1700

Data Index: 1501453 (The Pile)

Max Activating Token Index: 318

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.5361. Min Range: -3.5361

Max Act: 3.4264. Min Act: -0.1700

Data Index: 7478093 (The Pile)

Max Activating Token Index: 953

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.5361. Min Range: -3.5361

Max Act: 3.4421. Min Act: -0.1700

Data Index: 8656948 (The Pile)

Max Activating Token Index: 364

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.5361. Min Range: -3.5361

Max Act: 3.4264. Min Act: -0.1700

Data Index: 871984 (The Pile)

Max Activating Token Index: 146

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.5361. Min Range: -3.5361

Max Act: 3.4264. Min Act: -0.1700

Data Index: 4681091 (The Pile)

Max Activating Token Index: 271

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.5361. Min Range: -3.5361

Max Act: 3.4107. Min Act: -0.1700

Data Index: 6180461 (The Pile)

Max Activating Token Index: 228

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.5361. Min Range: -3.5361

Max Act: 3.4107. Min Act: -0.1700

Data Index: 6529699 (The Pile)

Max Activating Token Index: 1005

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.5361. Min Range: -3.5361

Max Act: 3.4264. Min Act: -0.1700

Data Index: 883823 (The Pile)

Max Activating Token Index: 355

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.5361. Min Range: -3.5361

Max Act: 3.4107. Min Act: -0.1700

Data Index: 5013586 (The Pile)

Max Activating Token Index: 679

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.5361. Min Range: -3.5361

Max Act: 3.4107. Min Act: -0.1700

Data Index: 3697845 (The Pile)

Max Activating Token Index: 725

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.5361. Min Range: -3.5361

Max Act: 3.4107. Min Act: -0.1700

Data Index: 2948897 (The Pile)

Max Activating Token Index: 990

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.5361. Min Range: -3.5361

Max Act: 3.3950. Min Act: -0.1700

Data Index: 8107707 (The Pile)

Max Activating Token Index: 297

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.5361. Min Range: -3.5361

Max Act: 3.4107. Min Act: -0.1700

Data Index: 7591048 (The Pile)

Max Activating Token Index: 130

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.5361. Min Range: -3.5361

Max Act: 3.3950. Min Act: -0.1700

Data Index: 6684767 (The Pile)

Max Activating Token Index: 191

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.5361. Min Range: -3.5361

Max Act: 3.3950. Min Act: -0.1700

Data Index: 2780989 (The Pile)

Max Activating Token Index: 186

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.5361. Min Range: -3.5361

Max Act: 3.3950. Min Act: -0.1700

Data Index: 5703143 (The Pile)

Max Activating Token Index: 837

Click toggle to see full text

Truncated

Full Text #19