< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 17 in Layer 35

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 12.7696. Min Range: -12.7696

Max Act: 12.7696. Min Act: -0.1700

Data Index: 3784022 (Open Web Text)

Max Activating Token Index: 694

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 12.7696. Min Range: -12.7696

Max Act: 12.4571. Min Act: -0.1700

Data Index: 2288459 (Open Web Text)

Max Activating Token Index: 133

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 12.7696. Min Range: -12.7696

Max Act: 12.2696. Min Act: -0.1700

Data Index: 390664 (Open Web Text)

Max Activating Token Index: 467

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 12.7696. Min Range: -12.7696

Max Act: 12.2071. Min Act: -0.1700

Data Index: 6347224 (Open Web Text)

Max Activating Token Index: 379

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 12.7696. Min Range: -12.7696

Max Act: 12.2696. Min Act: -0.1700

Data Index: 5245464 (Open Web Text)

Max Activating Token Index: 312

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 12.7696. Min Range: -12.7696

Max Act: 12.2696. Min Act: -0.1700

Data Index: 4767093 (Open Web Text)

Max Activating Token Index: 915

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 12.7696. Min Range: -12.7696

Max Act: 12.2071. Min Act: -0.1700

Data Index: 4687537 (Open Web Text)

Max Activating Token Index: 821

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 12.7696. Min Range: -12.7696

Max Act: 12.1446. Min Act: -0.1700

Data Index: 4379559 (Open Web Text)

Max Activating Token Index: 695

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 12.7696. Min Range: -12.7696

Max Act: 12.0821. Min Act: -0.1700

Data Index: 1705587 (Open Web Text)

Max Activating Token Index: 306

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 12.7696. Min Range: -12.7696

Max Act: 12.1446. Min Act: -0.1700

Data Index: 7929302 (Open Web Text)

Max Activating Token Index: 555

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 12.7696. Min Range: -12.7696

Max Act: 12.0196. Min Act: -0.1700

Data Index: 4576582 (Open Web Text)

Max Activating Token Index: 667

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 12.7696. Min Range: -12.7696

Max Act: 12.0821. Min Act: -0.1700

Data Index: 1556045 (Open Web Text)

Max Activating Token Index: 813

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 12.7696. Min Range: -12.7696

Max Act: 12.0821. Min Act: -0.1700

Data Index: 5735452 (Open Web Text)

Max Activating Token Index: 313

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 12.7696. Min Range: -12.7696

Max Act: 12.0821. Min Act: -0.1700

Data Index: 2876438 (Open Web Text)

Max Activating Token Index: 673

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 12.7696. Min Range: -12.7696

Max Act: 12.1446. Min Act: -0.1700

Data Index: 3165145 (Open Web Text)

Max Activating Token Index: 903

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 12.7696. Min Range: -12.7696

Max Act: 12.0821. Min Act: -0.1700

Data Index: 264485 (Open Web Text)

Max Activating Token Index: 321

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 12.7696. Min Range: -12.7696

Max Act: 12.0821. Min Act: -0.1695

Data Index: 3165159 (Open Web Text)

Max Activating Token Index: 820

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 12.7696. Min Range: -12.7696

Max Act: 12.0821. Min Act: -0.1700

Data Index: 1240784 (Open Web Text)

Max Activating Token Index: 778

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 12.7696. Min Range: -12.7696

Max Act: 12.0821. Min Act: -0.1700

Data Index: 5766549 (Open Web Text)

Max Activating Token Index: 372

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 12.7696. Min Range: -12.7696

Max Act: 12.1446. Min Act: -0.1700

Data Index: 6014209 (Open Web Text)

Max Activating Token Index: 612

Click toggle to see full text

Truncated

Full Text #19