< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 6342 in Layer 37

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 10.0603. Min Range: -10.0603

Max Act: 10.0603. Min Act: -0.1700

Data Index: 809436 (Open Web Text)

Max Activating Token Index: 1016

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 10.0603. Min Range: -10.0603

Max Act: 9.6853. Min Act: -0.1700

Data Index: 374793 (Open Web Text)

Max Activating Token Index: 513

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 10.0603. Min Range: -10.0603

Max Act: 9.5603. Min Act: -0.1700

Data Index: 893900 (Open Web Text)

Max Activating Token Index: 648

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 10.0603. Min Range: -10.0603

Max Act: 9.4353. Min Act: -0.1700

Data Index: 7247443 (Open Web Text)

Max Activating Token Index: 275

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 10.0603. Min Range: -10.0603

Max Act: 9.4978. Min Act: -0.1700

Data Index: 8654036 (Open Web Text)

Max Activating Token Index: 837

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 10.0603. Min Range: -10.0603

Max Act: 9.4353. Min Act: -0.1700

Data Index: 6764547 (Open Web Text)

Max Activating Token Index: 159

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 10.0603. Min Range: -10.0603

Max Act: 9.4353. Min Act: -0.1700

Data Index: 6964580 (Open Web Text)

Max Activating Token Index: 372

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 10.0603. Min Range: -10.0603

Max Act: 9.2478. Min Act: -0.1700

Data Index: 2874180 (Open Web Text)

Max Activating Token Index: 301

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 10.0603. Min Range: -10.0603

Max Act: 9.1853. Min Act: -0.1700

Data Index: 7613646 (Open Web Text)

Max Activating Token Index: 289

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 10.0603. Min Range: -10.0603

Max Act: 9.1853. Min Act: -0.1700

Data Index: 5160272 (Open Web Text)

Max Activating Token Index: 790

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 10.0603. Min Range: -10.0603

Max Act: 9.1228. Min Act: -0.1700

Data Index: 156210 (Open Web Text)

Max Activating Token Index: 159

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 10.0603. Min Range: -10.0603

Max Act: 9.2478. Min Act: -0.1700

Data Index: 1934767 (Open Web Text)

Max Activating Token Index: 581

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 10.0603. Min Range: -10.0603

Max Act: 9.0603. Min Act: -0.1700

Data Index: 3591086 (Open Web Text)

Max Activating Token Index: 212

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 10.0603. Min Range: -10.0603

Max Act: 9.1228. Min Act: -0.1700

Data Index: 1828379 (Open Web Text)

Max Activating Token Index: 497

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 10.0603. Min Range: -10.0603

Max Act: 8.8728. Min Act: -0.1700

Data Index: 4640730 (Open Web Text)

Max Activating Token Index: 972

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 10.0603. Min Range: -10.0603

Max Act: 8.8728. Min Act: -0.1700

Data Index: 8250224 (Open Web Text)

Max Activating Token Index: 53

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 10.0603. Min Range: -10.0603

Max Act: 8.8728. Min Act: -0.1700

Data Index: 3335263 (Open Web Text)

Max Activating Token Index: 131

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 10.0603. Min Range: -10.0603

Max Act: 8.8728. Min Act: -0.1700

Data Index: 4182517 (Open Web Text)

Max Activating Token Index: 916

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 10.0603. Min Range: -10.0603

Max Act: 8.8103. Min Act: -0.1700

Data Index: 3667115 (Open Web Text)

Max Activating Token Index: 89

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 10.0603. Min Range: -10.0603

Max Act: 8.8103. Min Act: -0.1700

Data Index: 4014705 (Open Web Text)

Max Activating Token Index: 600

Click toggle to see full text

Truncated

Full Text #19