< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 2 in Layer 43

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 16.5514. Min Range: -16.5514

Max Act: 16.5514. Min Act: -0.1700

Data Index: 2097295 (Open Web Text)

Max Activating Token Index: 753

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 16.5514. Min Range: -16.5514

Max Act: 16.5514. Min Act: -0.1700

Data Index: 254 (Open Web Text)

Max Activating Token Index: 1000

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 16.5514. Min Range: -16.5514

Max Act: 16.4264. Min Act: -0.1700

Data Index: 3410562 (Open Web Text)

Max Activating Token Index: 178

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 16.5514. Min Range: -16.5514

Max Act: 16.3014. Min Act: -0.1700

Data Index: 4637971 (Open Web Text)

Max Activating Token Index: 986

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 16.5514. Min Range: -16.5514

Max Act: 16.3014. Min Act: -0.1700

Data Index: 1812964 (Open Web Text)

Max Activating Token Index: 366

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 16.5514. Min Range: -16.5514

Max Act: 16.1764. Min Act: -0.1700

Data Index: 6795653 (Open Web Text)

Max Activating Token Index: 353

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 16.5514. Min Range: -16.5514

Max Act: 16.1764. Min Act: -0.1700

Data Index: 1504066 (Open Web Text)

Max Activating Token Index: 554

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 16.5514. Min Range: -16.5514

Max Act: 16.1764. Min Act: -0.1700

Data Index: 7971782 (Open Web Text)

Max Activating Token Index: 954

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 16.5514. Min Range: -16.5514

Max Act: 16.1764. Min Act: -0.1700

Data Index: 3210182 (Open Web Text)

Max Activating Token Index: 811

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 16.5514. Min Range: -16.5514

Max Act: 16.0514. Min Act: -0.1700

Data Index: 457855 (Open Web Text)

Max Activating Token Index: 616

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 16.5514. Min Range: -16.5514

Max Act: 16.0514. Min Act: -0.1700

Data Index: 1407625 (Open Web Text)

Max Activating Token Index: 376

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 16.5514. Min Range: -16.5514

Max Act: 16.0514. Min Act: -0.1700

Data Index: 2066233 (Open Web Text)

Max Activating Token Index: 403

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 16.5514. Min Range: -16.5514

Max Act: 16.0514. Min Act: -0.1700

Data Index: 4328911 (Open Web Text)

Max Activating Token Index: 844

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 16.5514. Min Range: -16.5514

Max Act: 16.0514. Min Act: -0.1700

Data Index: 4999662 (Open Web Text)

Max Activating Token Index: 595

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 16.5514. Min Range: -16.5514

Max Act: 16.0514. Min Act: -0.1700

Data Index: 7379477 (Open Web Text)

Max Activating Token Index: 791

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 16.5514. Min Range: -16.5514

Max Act: 16.0514. Min Act: -0.1700

Data Index: 4119775 (Open Web Text)

Max Activating Token Index: 970

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 16.5514. Min Range: -16.5514

Max Act: 15.9264. Min Act: -0.1700

Data Index: 1803450 (Open Web Text)

Max Activating Token Index: 672

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 16.5514. Min Range: -16.5514

Max Act: 15.9264. Min Act: -0.1700

Data Index: 4432851 (Open Web Text)

Max Activating Token Index: 575

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 16.5514. Min Range: -16.5514

Max Act: 15.9264. Min Act: -0.1700

Data Index: 2518922 (Open Web Text)

Max Activating Token Index: 674

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 16.5514. Min Range: -16.5514

Max Act: 15.9264. Min Act: -0.1700

Data Index: 5416362 (Open Web Text)

Max Activating Token Index: 431

Click toggle to see full text

Truncated

Full Text #19