< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 6378 in Layer 23

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 5.6617. Min Range: -5.6617

Max Act: 5.6617. Min Act: -0.1700

Data Index: 5185562 (Open Web Text)

Max Activating Token Index: 641

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 5.6617. Min Range: -5.6617

Max Act: 5.4429. Min Act: -0.1700

Data Index: 7148318 (Open Web Text)

Max Activating Token Index: 730

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 5.6617. Min Range: -5.6617

Max Act: 5.3492. Min Act: -0.1700

Data Index: 2954047 (Open Web Text)

Max Activating Token Index: 882

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 5.6617. Min Range: -5.6617

Max Act: 5.2867. Min Act: -0.1700

Data Index: 4167966 (Open Web Text)

Max Activating Token Index: 825

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 5.6617. Min Range: -5.6617

Max Act: 5.2554. Min Act: -0.1700

Data Index: 7354275 (Open Web Text)

Max Activating Token Index: 568

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 5.6617. Min Range: -5.6617

Max Act: 5.1304. Min Act: -0.1700

Data Index: 7361725 (Open Web Text)

Max Activating Token Index: 392

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 5.6617. Min Range: -5.6617

Max Act: 5.1304. Min Act: -0.1700

Data Index: 3897780 (Open Web Text)

Max Activating Token Index: 806

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 5.6617. Min Range: -5.6617

Max Act: 5.1304. Min Act: -0.1700

Data Index: 2855309 (Open Web Text)

Max Activating Token Index: 558

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 5.6617. Min Range: -5.6617

Max Act: 5.0992. Min Act: -0.1700

Data Index: 2394407 (Open Web Text)

Max Activating Token Index: 382

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 5.6617. Min Range: -5.6617

Max Act: 5.0992. Min Act: -0.1700

Data Index: 8681649 (Open Web Text)

Max Activating Token Index: 851

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 5.6617. Min Range: -5.6617

Max Act: 5.0679. Min Act: -0.1700

Data Index: 1872327 (Open Web Text)

Max Activating Token Index: 341

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 5.6617. Min Range: -5.6617

Max Act: 5.0992. Min Act: -0.1700

Data Index: 2618887 (Open Web Text)

Max Activating Token Index: 388

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 5.6617. Min Range: -5.6617

Max Act: 5.0679. Min Act: -0.1700

Data Index: 2652025 (Open Web Text)

Max Activating Token Index: 691

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 5.6617. Min Range: -5.6617

Max Act: 5.0992. Min Act: -0.1700

Data Index: 4194137 (Open Web Text)

Max Activating Token Index: 408

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 5.6617. Min Range: -5.6617

Max Act: 5.0679. Min Act: -0.1700

Data Index: 8270222 (Open Web Text)

Max Activating Token Index: 159

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 5.6617. Min Range: -5.6617

Max Act: 5.0367. Min Act: -0.1700

Data Index: 161977 (Open Web Text)

Max Activating Token Index: 249

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 5.6617. Min Range: -5.6617

Max Act: 5.0054. Min Act: -0.1700

Data Index: 113899 (Open Web Text)

Max Activating Token Index: 991

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 5.6617. Min Range: -5.6617

Max Act: 5.0367. Min Act: -0.1700

Data Index: 460011 (Open Web Text)

Max Activating Token Index: 391

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 5.6617. Min Range: -5.6617

Max Act: 5.0367. Min Act: -0.1700

Data Index: 5126156 (Open Web Text)

Max Activating Token Index: 429

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 5.6617. Min Range: -5.6617

Max Act: 5.0054. Min Act: -0.1700

Data Index: 4432726 (Open Web Text)

Max Activating Token Index: 1011

Click toggle to see full text

Truncated

Full Text #19