< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 26 in Layer 29

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 7.0878. Min Range: -7.0878

Max Act: 7.0878. Min Act: -0.1700

Data Index: 2929552 (Open Web Text)

Max Activating Token Index: 485

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 7.0878. Min Range: -7.0878

Max Act: 6.9315. Min Act: -0.1700

Data Index: 1723136 (Open Web Text)

Max Activating Token Index: 411

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 7.0878. Min Range: -7.0878

Max Act: 6.8378. Min Act: -0.1700

Data Index: 5827611 (Open Web Text)

Max Activating Token Index: 64

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 7.0878. Min Range: -7.0878

Max Act: 6.7440. Min Act: -0.1700

Data Index: 1306375 (Open Web Text)

Max Activating Token Index: 690

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 7.0878. Min Range: -7.0878

Max Act: 6.7440. Min Act: -0.1700

Data Index: 7566658 (Open Web Text)

Max Activating Token Index: 261

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 7.0878. Min Range: -7.0878

Max Act: 6.6503. Min Act: -0.1700

Data Index: 721105 (Open Web Text)

Max Activating Token Index: 486

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 7.0878. Min Range: -7.0878

Max Act: 6.6815. Min Act: -0.1700

Data Index: 1287258 (Open Web Text)

Max Activating Token Index: 116

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 7.0878. Min Range: -7.0878

Max Act: 6.6190. Min Act: -0.1700

Data Index: 3029474 (Open Web Text)

Max Activating Token Index: 699

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 7.0878. Min Range: -7.0878

Max Act: 6.5878. Min Act: -0.1700

Data Index: 5071329 (Open Web Text)

Max Activating Token Index: 275

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 7.0878. Min Range: -7.0878

Max Act: 6.5565. Min Act: -0.1700

Data Index: 7329130 (Open Web Text)

Max Activating Token Index: 971

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 7.0878. Min Range: -7.0878

Max Act: 6.5253. Min Act: -0.1700

Data Index: 3756597 (Open Web Text)

Max Activating Token Index: 410

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 7.0878. Min Range: -7.0878

Max Act: 6.4628. Min Act: -0.1700

Data Index: 7630885 (Open Web Text)

Max Activating Token Index: 260

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 7.0878. Min Range: -7.0878

Max Act: 6.4628. Min Act: -0.1700

Data Index: 6894783 (Open Web Text)

Max Activating Token Index: 373

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 7.0878. Min Range: -7.0878

Max Act: 6.4628. Min Act: -0.1700

Data Index: 3539747 (Open Web Text)

Max Activating Token Index: 800

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 7.0878. Min Range: -7.0878

Max Act: 6.4315. Min Act: -0.1700

Data Index: 6770557 (Open Web Text)

Max Activating Token Index: 431

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 7.0878. Min Range: -7.0878

Max Act: 6.4315. Min Act: -0.1700

Data Index: 2492761 (Open Web Text)

Max Activating Token Index: 671

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 7.0878. Min Range: -7.0878

Max Act: 6.4003. Min Act: -0.1700

Data Index: 7137429 (Open Web Text)

Max Activating Token Index: 137

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 7.0878. Min Range: -7.0878

Max Act: 6.3690. Min Act: -0.1700

Data Index: 8608122 (Open Web Text)

Max Activating Token Index: 701

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 7.0878. Min Range: -7.0878

Max Act: 6.3690. Min Act: -0.1700

Data Index: 3920856 (Open Web Text)

Max Activating Token Index: 828

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 7.0878. Min Range: -7.0878

Max Act: 6.3378. Min Act: -0.1700

Data Index: 5619574 (Open Web Text)

Max Activating Token Index: 463

Click toggle to see full text

Truncated

Full Text #19