< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 3070 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')



Text #0

Max Range: 4.0332. Min Range: -4.0332

Max Act: 4.0332. Min Act: -0.1700

Data Index: 776725 (The Pile)

Max Activating Token Index: 641

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.0332. Min Range: -4.0332

Max Act: 4.0020. Min Act: -0.1700

Data Index: 3147699 (The Pile)

Max Activating Token Index: 984

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.0332. Min Range: -4.0332

Max Act: 3.9551. Min Act: -0.1700

Data Index: 3762261 (The Pile)

Max Activating Token Index: 827

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.0332. Min Range: -4.0332

Max Act: 3.9238. Min Act: -0.1700

Data Index: 1785197 (The Pile)

Max Activating Token Index: 321

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.0332. Min Range: -4.0332

Max Act: 3.9238. Min Act: -0.1700

Data Index: 5417243 (The Pile)

Max Activating Token Index: 247

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.0332. Min Range: -4.0332

Max Act: 3.9238. Min Act: -0.1700

Data Index: 2400227 (The Pile)

Max Activating Token Index: 444

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.0332. Min Range: -4.0332

Max Act: 3.9238. Min Act: -0.1700

Data Index: 7314322 (The Pile)

Max Activating Token Index: 388

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.0332. Min Range: -4.0332

Max Act: 3.9081. Min Act: -0.1700

Data Index: 845469 (The Pile)

Max Activating Token Index: 527

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.0332. Min Range: -4.0332

Max Act: 3.8925. Min Act: -0.1700

Data Index: 4561364 (The Pile)

Max Activating Token Index: 439

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.0332. Min Range: -4.0332

Max Act: 3.8925. Min Act: -0.1700

Data Index: 7199600 (The Pile)

Max Activating Token Index: 237

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.0332. Min Range: -4.0332

Max Act: 3.8925. Min Act: -0.1700

Data Index: 10118088 (The Pile)

Max Activating Token Index: 526

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.0332. Min Range: -4.0332

Max Act: 3.8612. Min Act: -0.1700

Data Index: 7067903 (The Pile)

Max Activating Token Index: 373

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.0332. Min Range: -4.0332

Max Act: 3.8612. Min Act: -0.1700

Data Index: 2566776 (The Pile)

Max Activating Token Index: 392

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.0332. Min Range: -4.0332

Max Act: 3.8456. Min Act: -0.1700

Data Index: 2281598 (The Pile)

Max Activating Token Index: 145

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.0332. Min Range: -4.0332

Max Act: 3.8456. Min Act: -0.1700

Data Index: 5334014 (The Pile)

Max Activating Token Index: 389

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.0332. Min Range: -4.0332

Max Act: 3.8456. Min Act: -0.1700

Data Index: 9412225 (The Pile)

Max Activating Token Index: 690

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.0332. Min Range: -4.0332

Max Act: 3.8300. Min Act: -0.1700

Data Index: 10722597 (The Pile)

Max Activating Token Index: 533

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.0332. Min Range: -4.0332

Max Act: 3.8300. Min Act: -0.1700

Data Index: 7000840 (The Pile)

Max Activating Token Index: 753

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.0332. Min Range: -4.0332

Max Act: 3.8300. Min Act: -0.1700

Data Index: 3110260 (The Pile)

Max Activating Token Index: 872

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.0332. Min Range: -4.0332

Max Act: 3.8143. Min Act: -0.1700

Data Index: 8341016 (The Pile)

Max Activating Token Index: 785

Click toggle to see full text

Truncated

Full Text #19