< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 2014 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: 2.9897. Min Range: -2.9897

Max Act: 2.9897. Min Act: -0.1700

Data Index: 3651959 (The Pile)

Max Activating Token Index: 294

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.9897. Min Range: -2.9897

Max Act: 2.9897. Min Act: -0.1700

Data Index: 10514641 (The Pile)

Max Activating Token Index: 921

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.9897. Min Range: -2.9897

Max Act: 2.9422. Min Act: -0.1700

Data Index: 2196463 (The Pile)

Max Activating Token Index: 528

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.9897. Min Range: -2.9897

Max Act: 2.9581. Min Act: -0.1700

Data Index: 8331589 (The Pile)

Max Activating Token Index: 352

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.9897. Min Range: -2.9897

Max Act: 2.9581. Min Act: -0.1700

Data Index: 3648640 (The Pile)

Max Activating Token Index: 181

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.9897. Min Range: -2.9897

Max Act: 2.9422. Min Act: -0.1700

Data Index: 6197326 (The Pile)

Max Activating Token Index: 732

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.9897. Min Range: -2.9897

Max Act: 2.9264. Min Act: -0.1700

Data Index: 8285615 (The Pile)

Max Activating Token Index: 213

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.9897. Min Range: -2.9897

Max Act: 2.9264. Min Act: -0.1700

Data Index: 9948323 (The Pile)

Max Activating Token Index: 923

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.9897. Min Range: -2.9897

Max Act: 2.8947. Min Act: -0.1700

Data Index: 2859284 (The Pile)

Max Activating Token Index: 725

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.9897. Min Range: -2.9897

Max Act: 2.9422. Min Act: -0.1700

Data Index: 6313945 (The Pile)

Max Activating Token Index: 619

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.9897. Min Range: -2.9897

Max Act: 2.9264. Min Act: -0.1700

Data Index: 1503375 (The Pile)

Max Activating Token Index: 663

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.9897. Min Range: -2.9897

Max Act: 2.9264. Min Act: -0.1700

Data Index: 820022 (The Pile)

Max Activating Token Index: 485

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.9897. Min Range: -2.9897

Max Act: 2.9264. Min Act: -0.1700

Data Index: 4844166 (The Pile)

Max Activating Token Index: 810

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.9897. Min Range: -2.9897

Max Act: 2.9264. Min Act: -0.1700

Data Index: 9646769 (The Pile)

Max Activating Token Index: 486

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.9897. Min Range: -2.9897

Max Act: 2.9264. Min Act: -0.1700

Data Index: 4374927 (The Pile)

Max Activating Token Index: 467

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.9897. Min Range: -2.9897

Max Act: 2.9105. Min Act: -0.1700

Data Index: 3197454 (The Pile)

Max Activating Token Index: 302

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.9897. Min Range: -2.9897

Max Act: 2.9264. Min Act: -0.1700

Data Index: 8513344 (The Pile)

Max Activating Token Index: 744

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.9897. Min Range: -2.9897

Max Act: 2.9105. Min Act: -0.1700

Data Index: 4222983 (The Pile)

Max Activating Token Index: 196

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.9897. Min Range: -2.9897

Max Act: 2.9105. Min Act: -0.1700

Data Index: 7660432 (The Pile)

Max Activating Token Index: 294

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.9897. Min Range: -2.9897

Max Act: 2.9105. Min Act: -0.1700

Data Index: 5628928 (The Pile)

Max Activating Token Index: 632

Click toggle to see full text

Truncated

Full Text #19