< Prev | Home | Model | Random | Next >

Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 6399 in Layer 28

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')



Text #0

Max Range: 10.1638. Min Range: -10.1638

Max Act: 10.1638. Min Act: -0.1700

Data Index: 4917180 (Open Web Text)

Max Activating Token Index: 874

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 10.1638. Min Range: -10.1638

Max Act: 10.0388. Min Act: -0.1700

Data Index: 44056 (Open Web Text)

Max Activating Token Index: 882

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 10.1638. Min Range: -10.1638

Max Act: 9.9763. Min Act: -0.1700

Data Index: 4110968 (Open Web Text)

Max Activating Token Index: 543

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 10.1638. Min Range: -10.1638

Max Act: 9.9138. Min Act: -0.1700

Data Index: 2576396 (Open Web Text)

Max Activating Token Index: 302

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 10.1638. Min Range: -10.1638

Max Act: 9.9138. Min Act: -0.1700

Data Index: 2215572 (Open Web Text)

Max Activating Token Index: 349

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 10.1638. Min Range: -10.1638

Max Act: 9.9138. Min Act: -0.1700

Data Index: 660638 (Open Web Text)

Max Activating Token Index: 572

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 10.1638. Min Range: -10.1638

Max Act: 9.8513. Min Act: -0.1700

Data Index: 7281267 (Open Web Text)

Max Activating Token Index: 652

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 10.1638. Min Range: -10.1638

Max Act: 9.9138. Min Act: -0.1700

Data Index: 1269405 (Open Web Text)

Max Activating Token Index: 802

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 10.1638. Min Range: -10.1638

Max Act: 9.7888. Min Act: -0.1700

Data Index: 3444886 (Open Web Text)

Max Activating Token Index: 99

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 10.1638. Min Range: -10.1638

Max Act: 9.7263. Min Act: -0.1700

Data Index: 2139088 (Open Web Text)

Max Activating Token Index: 614

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 10.1638. Min Range: -10.1638

Max Act: 9.7263. Min Act: -0.1700

Data Index: 7429319 (Open Web Text)

Max Activating Token Index: 204

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 10.1638. Min Range: -10.1638

Max Act: 9.6638. Min Act: -0.1700

Data Index: 7821259 (Open Web Text)

Max Activating Token Index: 786

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 10.1638. Min Range: -10.1638

Max Act: 9.6638. Min Act: -0.1700

Data Index: 8311537 (Open Web Text)

Max Activating Token Index: 339

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 10.1638. Min Range: -10.1638

Max Act: 9.6638. Min Act: -0.1700

Data Index: 3843373 (Open Web Text)

Max Activating Token Index: 906

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 10.1638. Min Range: -10.1638

Max Act: 9.6638. Min Act: -0.1700

Data Index: 4582674 (Open Web Text)

Max Activating Token Index: 345

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 10.1638. Min Range: -10.1638

Max Act: 9.6638. Min Act: -0.1700

Data Index: 1586124 (Open Web Text)

Max Activating Token Index: 749

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 10.1638. Min Range: -10.1638

Max Act: 9.6013. Min Act: -0.1700

Data Index: 7125240 (Open Web Text)

Max Activating Token Index: 259

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 10.1638. Min Range: -10.1638

Max Act: 9.5388. Min Act: -0.1700

Data Index: 578622 (Open Web Text)

Max Activating Token Index: 725

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 10.1638. Min Range: -10.1638

Max Act: 9.6013. Min Act: -0.1700

Data Index: 1709518 (Open Web Text)

Max Activating Token Index: 539

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 10.1638. Min Range: -10.1638

Max Act: 9.6013. Min Act: -0.1700

Data Index: 5618602 (Open Web Text)

Max Activating Token Index: 486

Click toggle to see full text

Truncated

Full Text #19