< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 6399 in Layer 21

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 4.8151. Min Range: -4.8151

Max Act: 4.8151. Min Act: -0.1700

Data Index: 4376554 (Open Web Text)

Max Activating Token Index: 665

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.8151. Min Range: -4.8151

Max Act: 4.8151. Min Act: -0.1700

Data Index: 3210386 (Open Web Text)

Max Activating Token Index: 589

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.8151. Min Range: -4.8151

Max Act: 4.7526. Min Act: -0.1700

Data Index: 5492383 (Open Web Text)

Max Activating Token Index: 747

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.8151. Min Range: -4.8151

Max Act: 4.7214. Min Act: -0.1700

Data Index: 2253261 (Open Web Text)

Max Activating Token Index: 22

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.8151. Min Range: -4.8151

Max Act: 4.7526. Min Act: -0.1700

Data Index: 5054717 (Open Web Text)

Max Activating Token Index: 186

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.8151. Min Range: -4.8151

Max Act: 4.6589. Min Act: -0.1700

Data Index: 4833100 (Open Web Text)

Max Activating Token Index: 505

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.8151. Min Range: -4.8151

Max Act: 4.6589. Min Act: -0.1700

Data Index: 4098554 (Open Web Text)

Max Activating Token Index: 999

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.8151. Min Range: -4.8151

Max Act: 4.6589. Min Act: -0.1700

Data Index: 6829287 (Open Web Text)

Max Activating Token Index: 867

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.8151. Min Range: -4.8151

Max Act: 4.5964. Min Act: -0.1700

Data Index: 1877631 (Open Web Text)

Max Activating Token Index: 414

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.8151. Min Range: -4.8151

Max Act: 4.6276. Min Act: -0.1700

Data Index: 6351771 (Open Web Text)

Max Activating Token Index: 256

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.8151. Min Range: -4.8151

Max Act: 4.6276. Min Act: -0.1700

Data Index: 7365895 (Open Web Text)

Max Activating Token Index: 473

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.8151. Min Range: -4.8151

Max Act: 4.5964. Min Act: -0.1700

Data Index: 937218 (Open Web Text)

Max Activating Token Index: 692

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.8151. Min Range: -4.8151

Max Act: 4.5651. Min Act: -0.1700

Data Index: 2353669 (Open Web Text)

Max Activating Token Index: 332

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.8151. Min Range: -4.8151

Max Act: 4.5964. Min Act: -0.1700

Data Index: 3132422 (Open Web Text)

Max Activating Token Index: 174

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.8151. Min Range: -4.8151

Max Act: 4.5339. Min Act: -0.1700

Data Index: 4559545 (Open Web Text)

Max Activating Token Index: 614

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.8151. Min Range: -4.8151

Max Act: 4.5651. Min Act: -0.1700

Data Index: 247023 (Open Web Text)

Max Activating Token Index: 174

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.8151. Min Range: -4.8151

Max Act: 4.5651. Min Act: -0.1700

Data Index: 1213527 (Open Web Text)

Max Activating Token Index: 738

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.8151. Min Range: -4.8151

Max Act: 4.5339. Min Act: -0.1700

Data Index: 1475314 (Open Web Text)

Max Activating Token Index: 34

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.8151. Min Range: -4.8151

Max Act: 4.5651. Min Act: -0.1700

Data Index: 366102 (Open Web Text)

Max Activating Token Index: 779

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.8151. Min Range: -4.8151

Max Act: 4.5339. Min Act: -0.1700

Data Index: 5332024 (Open Web Text)

Max Activating Token Index: 495

Click toggle to see full text

Truncated

Full Text #19