< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 2009 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 2.8479. Min Range: -2.8479

Max Act: 2.8479. Min Act: -0.1700

Data Index: 5371606 (The Pile)

Max Activating Token Index: 710

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.8479. Min Range: -2.8479

Max Act: 2.8320. Min Act: -0.1700

Data Index: 3922084 (The Pile)

Max Activating Token Index: 656

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.8479. Min Range: -2.8479

Max Act: 2.8161. Min Act: -0.1700

Data Index: 2873317 (The Pile)

Max Activating Token Index: 928

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.8479. Min Range: -2.8479

Max Act: 2.8002. Min Act: -0.1700

Data Index: 9630835 (The Pile)

Max Activating Token Index: 509

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.8479. Min Range: -2.8479

Max Act: 2.7843. Min Act: -0.1700

Data Index: 5795369 (The Pile)

Max Activating Token Index: 608

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.8479. Min Range: -2.8479

Max Act: 2.7683. Min Act: -0.1700

Data Index: 6895033 (The Pile)

Max Activating Token Index: 506

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.8479. Min Range: -2.8479

Max Act: 2.7843. Min Act: -0.1700

Data Index: 6799177 (The Pile)

Max Activating Token Index: 453

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.8479. Min Range: -2.8479

Max Act: 2.7843. Min Act: -0.1700

Data Index: 9719832 (The Pile)

Max Activating Token Index: 137

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.8479. Min Range: -2.8479

Max Act: 2.7364. Min Act: -0.1700

Data Index: 5826647 (The Pile)

Max Activating Token Index: 975

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.8479. Min Range: -2.8479

Max Act: 2.7683. Min Act: -0.1700

Data Index: 6777919 (The Pile)

Max Activating Token Index: 894

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.8479. Min Range: -2.8479

Max Act: 2.7364. Min Act: -0.1700

Data Index: 8907939 (The Pile)

Max Activating Token Index: 232

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.8479. Min Range: -2.8479

Max Act: 2.7683. Min Act: -0.1700

Data Index: 3369588 (The Pile)

Max Activating Token Index: 212

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.8479. Min Range: -2.8479

Max Act: 2.7683. Min Act: -0.1700

Data Index: 169916 (The Pile)

Max Activating Token Index: 430

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.8479. Min Range: -2.8479

Max Act: 2.7683. Min Act: -0.1700

Data Index: 7545449 (The Pile)

Max Activating Token Index: 228

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.8479. Min Range: -2.8479

Max Act: 2.7683. Min Act: -0.1700

Data Index: 3963213 (The Pile)

Max Activating Token Index: 382

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.8479. Min Range: -2.8479

Max Act: 2.7524. Min Act: -0.1700

Data Index: 9625992 (The Pile)

Max Activating Token Index: 503

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.8479. Min Range: -2.8479

Max Act: 2.7524. Min Act: -0.1700

Data Index: 2500852 (The Pile)

Max Activating Token Index: 456

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.8479. Min Range: -2.8479

Max Act: 2.7524. Min Act: -0.1700

Data Index: 8881994 (The Pile)

Max Activating Token Index: 101

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.8479. Min Range: -2.8479

Max Act: 2.7364. Min Act: -0.1700

Data Index: 108200 (The Pile)

Max Activating Token Index: 137

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.8479. Min Range: -2.8479

Max Act: 2.7364. Min Act: -0.1700

Data Index: 2335649 (The Pile)

Max Activating Token Index: 227

Click toggle to see full text

Truncated

Full Text #19