< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 35 in Layer 39

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 15.9668. Min Range: -15.9668

Max Act: 15.9668. Min Act: -0.1700

Data Index: 2000635 (Open Web Text)

Max Activating Token Index: 768

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 15.9668. Min Range: -15.9668

Max Act: 15.7168. Min Act: -0.1700

Data Index: 6556690 (Open Web Text)

Max Activating Token Index: 218

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 15.9668. Min Range: -15.9668

Max Act: 15.4043. Min Act: -0.1700

Data Index: 4084174 (Open Web Text)

Max Activating Token Index: 923

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 15.9668. Min Range: -15.9668

Max Act: 15.4668. Min Act: -0.1700

Data Index: 7763979 (Open Web Text)

Max Activating Token Index: 730

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 15.9668. Min Range: -15.9668

Max Act: 15.5293. Min Act: -0.1700

Data Index: 1648240 (Open Web Text)

Max Activating Token Index: 559

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 15.9668. Min Range: -15.9668

Max Act: 15.4668. Min Act: -0.1700

Data Index: 4182853 (Open Web Text)

Max Activating Token Index: 242

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 15.9668. Min Range: -15.9668

Max Act: 15.2793. Min Act: -0.1700

Data Index: 8276835 (Open Web Text)

Max Activating Token Index: 673

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 15.9668. Min Range: -15.9668

Max Act: 15.2793. Min Act: -0.1700

Data Index: 4087332 (Open Web Text)

Max Activating Token Index: 172

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 15.9668. Min Range: -15.9668

Max Act: 15.2793. Min Act: -0.1700

Data Index: 446734 (Open Web Text)

Max Activating Token Index: 581

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 15.9668. Min Range: -15.9668

Max Act: 15.2168. Min Act: -0.1700

Data Index: 2960298 (Open Web Text)

Max Activating Token Index: 480

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 15.9668. Min Range: -15.9668

Max Act: 15.2168. Min Act: -0.1700

Data Index: 673569 (Open Web Text)

Max Activating Token Index: 427

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 15.9668. Min Range: -15.9668

Max Act: 15.2168. Min Act: -0.1700

Data Index: 7367999 (Open Web Text)

Max Activating Token Index: 464

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 15.9668. Min Range: -15.9668

Max Act: 15.2168. Min Act: -0.1700

Data Index: 431492 (Open Web Text)

Max Activating Token Index: 791

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 15.9668. Min Range: -15.9668

Max Act: 15.1543. Min Act: -0.1700

Data Index: 1952373 (Open Web Text)

Max Activating Token Index: 897

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 15.9668. Min Range: -15.9668

Max Act: 15.0918. Min Act: -0.1700

Data Index: 2591405 (Open Web Text)

Max Activating Token Index: 426

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 15.9668. Min Range: -15.9668

Max Act: 15.1543. Min Act: -0.1700

Data Index: 8790342 (Open Web Text)

Max Activating Token Index: 258

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 15.9668. Min Range: -15.9668

Max Act: 15.1543. Min Act: -0.1700

Data Index: 562422 (Open Web Text)

Max Activating Token Index: 984

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 15.9668. Min Range: -15.9668

Max Act: 15.1543. Min Act: -0.1700

Data Index: 7696951 (Open Web Text)

Max Activating Token Index: 948

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 15.9668. Min Range: -15.9668

Max Act: 15.0918. Min Act: -0.1700

Data Index: 1890487 (Open Web Text)

Max Activating Token Index: 293

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 15.9668. Min Range: -15.9668

Max Act: 15.0293. Min Act: -0.1700

Data Index: 5360850 (Open Web Text)

Max Activating Token Index: 420

Click toggle to see full text

Truncated

Full Text #19