< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 2007 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.6445. Min Range: -1.6445

Max Act: 1.6445. Min Act: -0.1700

Data Index: 977 (The Pile)

Max Activating Token Index: 145

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.6445. Min Range: -1.6445

Max Act: 1.6445. Min Act: -0.1700

Data Index: 13560 (The Pile)

Max Activating Token Index: 267

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.6445. Min Range: -1.6445

Max Act: 1.6445. Min Act: -0.1700

Data Index: 12547 (The Pile)

Max Activating Token Index: 599

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.6445. Min Range: -1.6445

Max Act: 1.6445. Min Act: -0.1700

Data Index: 11921 (The Pile)

Max Activating Token Index: 409

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.6445. Min Range: -1.6445

Max Act: 1.6445. Min Act: -0.1700

Data Index: 1331 (The Pile)

Max Activating Token Index: 594

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.6445. Min Range: -1.6445

Max Act: 1.6445. Min Act: -0.1700

Data Index: 515 (The Pile)

Max Activating Token Index: 985

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.6445. Min Range: -1.6445

Max Act: 1.6445. Min Act: -0.1700

Data Index: 16665 (The Pile)

Max Activating Token Index: 505

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.6445. Min Range: -1.6445

Max Act: 1.6445. Min Act: -0.1700

Data Index: 2597 (The Pile)

Max Activating Token Index: 552

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.6445. Min Range: -1.6445

Max Act: 1.6445. Min Act: -0.1700

Data Index: 2291 (The Pile)

Max Activating Token Index: 323

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.6445. Min Range: -1.6445

Max Act: 1.6445. Min Act: -0.1700

Data Index: 9242 (The Pile)

Max Activating Token Index: 224

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.6445. Min Range: -1.6445

Max Act: 1.6445. Min Act: -0.1700

Data Index: 14327 (The Pile)

Max Activating Token Index: 794

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.6445. Min Range: -1.6445

Max Act: 1.6445. Min Act: -0.1700

Data Index: 1908 (The Pile)

Max Activating Token Index: 452

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.6445. Min Range: -1.6445

Max Act: 1.6445. Min Act: -0.1700

Data Index: 8989 (The Pile)

Max Activating Token Index: 398

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.6445. Min Range: -1.6445

Max Act: 1.6445. Min Act: -0.1700

Data Index: 16402 (The Pile)

Max Activating Token Index: 177

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.6445. Min Range: -1.6445

Max Act: 1.6445. Min Act: -0.1700

Data Index: 7250 (The Pile)

Max Activating Token Index: 641

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.6445. Min Range: -1.6445

Max Act: 1.6445. Min Act: -0.1700

Data Index: 6484 (The Pile)

Max Activating Token Index: 476

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.6445. Min Range: -1.6445

Max Act: 1.6445. Min Act: -0.1700

Data Index: 15435 (The Pile)

Max Activating Token Index: 769

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.6445. Min Range: -1.6445

Max Act: 1.6445. Min Act: -0.1700

Data Index: 5887 (The Pile)

Max Activating Token Index: 221

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.6445. Min Range: -1.6445

Max Act: 1.6445. Min Act: -0.1700

Data Index: 5544 (The Pile)

Max Activating Token Index: 612

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.6445. Min Range: -1.6445

Max Act: 1.6445. Min Act: -0.1700

Data Index: 15172 (The Pile)

Max Activating Token Index: 643

Click toggle to see full text

Truncated

Full Text #19