< Prev | Home | Model | Random | Next >

Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer

Dataset: Open Web Text

Neuron 5110 in Layer 30

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 10.0582. Min Range: -10.0582

Max Act: 10.0582. Min Act: -0.1700

Data Index: 8681905 (Open Web Text)

Max Activating Token Index: 539

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 10.0582. Min Range: -10.0582

Max Act: 9.4957. Min Act: -0.1700

Data Index: 3872840 (Open Web Text)

Max Activating Token Index: 631

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 10.0582. Min Range: -10.0582

Max Act: 9.3707. Min Act: -0.1700

Data Index: 6814662 (Open Web Text)

Max Activating Token Index: 928

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 10.0582. Min Range: -10.0582

Max Act: 9.2457. Min Act: -0.1700

Data Index: 6110804 (Open Web Text)

Max Activating Token Index: 919

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 10.0582. Min Range: -10.0582

Max Act: 9.2457. Min Act: -0.1700

Data Index: 415592 (Open Web Text)

Max Activating Token Index: 421

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 10.0582. Min Range: -10.0582

Max Act: 9.1207. Min Act: -0.1700

Data Index: 8136508 (Open Web Text)

Max Activating Token Index: 345

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 10.0582. Min Range: -10.0582

Max Act: 9.1832. Min Act: -0.1700

Data Index: 7692861 (Open Web Text)

Max Activating Token Index: 394

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 10.0582. Min Range: -10.0582

Max Act: 9.1207. Min Act: -0.1700

Data Index: 2562778 (Open Web Text)

Max Activating Token Index: 779

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 10.0582. Min Range: -10.0582

Max Act: 9.1207. Min Act: -0.1700

Data Index: 5068464 (Open Web Text)

Max Activating Token Index: 737

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 10.0582. Min Range: -10.0582

Max Act: 9.1207. Min Act: -0.1700

Data Index: 7725664 (Open Web Text)

Max Activating Token Index: 667

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 10.0582. Min Range: -10.0582

Max Act: 9.1207. Min Act: -0.1700

Data Index: 7241288 (Open Web Text)

Max Activating Token Index: 656

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 10.0582. Min Range: -10.0582

Max Act: 9.0582. Min Act: -0.1700

Data Index: 6247356 (Open Web Text)

Max Activating Token Index: 399

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 10.0582. Min Range: -10.0582

Max Act: 9.0582. Min Act: -0.1700

Data Index: 6462862 (Open Web Text)

Max Activating Token Index: 940

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 10.0582. Min Range: -10.0582

Max Act: 9.0582. Min Act: -0.1700

Data Index: 6496133 (Open Web Text)

Max Activating Token Index: 659

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 10.0582. Min Range: -10.0582

Max Act: 9.0582. Min Act: -0.1700

Data Index: 5292090 (Open Web Text)

Max Activating Token Index: 494

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 10.0582. Min Range: -10.0582

Max Act: 8.9957. Min Act: -0.1700

Data Index: 1018895 (Open Web Text)

Max Activating Token Index: 570

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 10.0582. Min Range: -10.0582

Max Act: 8.9957. Min Act: -0.1700

Data Index: 6015322 (Open Web Text)

Max Activating Token Index: 1017

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 10.0582. Min Range: -10.0582

Max Act: 8.9332. Min Act: -0.1700

Data Index: 7972729 (Open Web Text)

Max Activating Token Index: 549

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 10.0582. Min Range: -10.0582

Max Act: 8.9957. Min Act: -0.1700

Data Index: 2663503 (Open Web Text)

Max Activating Token Index: 619

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 10.0582. Min Range: -10.0582

Max Act: 8.9332. Min Act: -0.1700

Data Index: 541259 (Open Web Text)

Max Activating Token Index: 683

Click toggle to see full text

Truncated

Full Text #19