< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 6361 in Layer 40

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 6.3587. Min Range: -6.3587

Max Act: 6.3587. Min Act: -0.1700

Data Index: 1381777 (Open Web Text)

Max Activating Token Index: 462

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 6.3587. Min Range: -6.3587

Max Act: 6.2337. Min Act: -0.1700

Data Index: 8774619 (Open Web Text)

Max Activating Token Index: 631

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 6.3587. Min Range: -6.3587

Max Act: 6.1712. Min Act: -0.1700

Data Index: 4805525 (Open Web Text)

Max Activating Token Index: 601

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 6.3587. Min Range: -6.3587

Max Act: 6.1399. Min Act: -0.1700

Data Index: 7490444 (Open Web Text)

Max Activating Token Index: 448

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 6.3587. Min Range: -6.3587

Max Act: 6.0149. Min Act: -0.1700

Data Index: 3869281 (Open Web Text)

Max Activating Token Index: 671

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 6.3587. Min Range: -6.3587

Max Act: 6.0462. Min Act: -0.1700

Data Index: 492094 (Open Web Text)

Max Activating Token Index: 408

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 6.3587. Min Range: -6.3587

Max Act: 6.0462. Min Act: -0.1700

Data Index: 4617554 (Open Web Text)

Max Activating Token Index: 318

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 6.3587. Min Range: -6.3587

Max Act: 5.9837. Min Act: -0.1700

Data Index: 1610316 (Open Web Text)

Max Activating Token Index: 733

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 6.3587. Min Range: -6.3587

Max Act: 5.9837. Min Act: -0.1700

Data Index: 2387382 (Open Web Text)

Max Activating Token Index: 257

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 6.3587. Min Range: -6.3587

Max Act: 5.9837. Min Act: -0.1700

Data Index: 1551168 (Open Web Text)

Max Activating Token Index: 420

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 6.3587. Min Range: -6.3587

Max Act: 5.9837. Min Act: -0.1700

Data Index: 8729029 (Open Web Text)

Max Activating Token Index: 113

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 6.3587. Min Range: -6.3587

Max Act: 5.9837. Min Act: -0.1700

Data Index: 388111 (Open Web Text)

Max Activating Token Index: 930

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 6.3587. Min Range: -6.3587

Max Act: 5.9524. Min Act: -0.1700

Data Index: 8134839 (Open Web Text)

Max Activating Token Index: 169

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 6.3587. Min Range: -6.3587

Max Act: 6.0149. Min Act: -0.1700

Data Index: 3118731 (Open Web Text)

Max Activating Token Index: 342

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 6.3587. Min Range: -6.3587

Max Act: 5.9837. Min Act: -0.1700

Data Index: 7600506 (Open Web Text)

Max Activating Token Index: 588

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 6.3587. Min Range: -6.3587

Max Act: 5.9212. Min Act: -0.1700

Data Index: 2331591 (Open Web Text)

Max Activating Token Index: 786

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 6.3587. Min Range: -6.3587

Max Act: 5.9212. Min Act: -0.1700

Data Index: 8731419 (Open Web Text)

Max Activating Token Index: 540

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 6.3587. Min Range: -6.3587

Max Act: 5.9212. Min Act: -0.1700

Data Index: 2707222 (Open Web Text)

Max Activating Token Index: 885

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 6.3587. Min Range: -6.3587

Max Act: 5.9212. Min Act: -0.1700

Data Index: 1518913 (Open Web Text)

Max Activating Token Index: 929

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 6.3587. Min Range: -6.3587

Max Act: 5.8587. Min Act: -0.1700

Data Index: 3856274 (Open Web Text)

Max Activating Token Index: 1009

Click toggle to see full text

Truncated

Full Text #19