< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 109 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 4.6081. Min Range: -4.6081

Max Act: 4.6081. Min Act: -0.1700

Data Index: 2788745 (The Pile)

Max Activating Token Index: 211

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.6081. Min Range: -4.6081

Max Act: 4.5456. Min Act: -0.1700

Data Index: 5000159 (The Pile)

Max Activating Token Index: 228

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.6081. Min Range: -4.6081

Max Act: 4.5456. Min Act: -0.1700

Data Index: 2296885 (The Pile)

Max Activating Token Index: 364

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.6081. Min Range: -4.6081

Max Act: 4.5456. Min Act: -0.1700

Data Index: 7929122 (The Pile)

Max Activating Token Index: 152

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.6081. Min Range: -4.6081

Max Act: 4.5456. Min Act: -0.1700

Data Index: 560472 (The Pile)

Max Activating Token Index: 517

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.6081. Min Range: -4.6081

Max Act: 4.5456. Min Act: -0.1700

Data Index: 7007570 (The Pile)

Max Activating Token Index: 270

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.6081. Min Range: -4.6081

Max Act: 4.5456. Min Act: -0.1700

Data Index: 9839194 (The Pile)

Max Activating Token Index: 283

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.6081. Min Range: -4.6081

Max Act: 4.5456. Min Act: -0.1700

Data Index: 4288883 (The Pile)

Max Activating Token Index: 178

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.6081. Min Range: -4.6081

Max Act: 4.5143. Min Act: -0.1700

Data Index: 6926725 (The Pile)

Max Activating Token Index: 260

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.6081. Min Range: -4.6081

Max Act: 4.5143. Min Act: -0.1700

Data Index: 8845280 (The Pile)

Max Activating Token Index: 190

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.6081. Min Range: -4.6081

Max Act: 4.5143. Min Act: -0.1700

Data Index: 3933809 (The Pile)

Max Activating Token Index: 139

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.6081. Min Range: -4.6081

Max Act: 4.5456. Min Act: -0.1700

Data Index: 4953842 (The Pile)

Max Activating Token Index: 481

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.6081. Min Range: -4.6081

Max Act: 4.5143. Min Act: -0.1700

Data Index: 8159518 (The Pile)

Max Activating Token Index: 834

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.6081. Min Range: -4.6081

Max Act: 4.5456. Min Act: -0.1700

Data Index: 1170976 (The Pile)

Max Activating Token Index: 454

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.6081. Min Range: -4.6081

Max Act: 4.5143. Min Act: -0.1700

Data Index: 5158262 (The Pile)

Max Activating Token Index: 899

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.6081. Min Range: -4.6081

Max Act: 4.5143. Min Act: -0.1700

Data Index: 8016265 (The Pile)

Max Activating Token Index: 298

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.6081. Min Range: -4.6081

Max Act: 4.5143. Min Act: -0.1700

Data Index: 183406 (The Pile)

Max Activating Token Index: 509

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.6081. Min Range: -4.6081

Max Act: 4.4831. Min Act: -0.1700

Data Index: 7088473 (The Pile)

Max Activating Token Index: 196

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.6081. Min Range: -4.6081

Max Act: 4.4831. Min Act: -0.1700

Data Index: 7425395 (The Pile)

Max Activating Token Index: 157

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.6081. Min Range: -4.6081

Max Act: 4.4831. Min Act: -0.1700

Data Index: 7807 (The Pile)

Max Activating Token Index: 646

Click toggle to see full text

Truncated

Full Text #19