< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 20 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: 15.3501. Min Range: -15.3501

Max Act: 15.2876. Min Act: -0.1700

Data Index: 6474346 (Open Web Text)

Max Activating Token Index: 278

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 15.3501. Min Range: -15.3501

Max Act: 15.3501. Min Act: -0.1700

Data Index: 5491333 (Open Web Text)

Max Activating Token Index: 644

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 15.3501. Min Range: -15.3501

Max Act: 15.2251. Min Act: -0.1700

Data Index: 6290436 (Open Web Text)

Max Activating Token Index: 853

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 15.3501. Min Range: -15.3501

Max Act: 15.1626. Min Act: -0.1700

Data Index: 5491332 (Open Web Text)

Max Activating Token Index: 295

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 15.3501. Min Range: -15.3501

Max Act: 15.1626. Min Act: -0.1700

Data Index: 3443932 (Open Web Text)

Max Activating Token Index: 360

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 15.3501. Min Range: -15.3501

Max Act: 15.1001. Min Act: -0.1700

Data Index: 6886001 (Open Web Text)

Max Activating Token Index: 590

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 15.3501. Min Range: -15.3501

Max Act: 15.1001. Min Act: -0.1700

Data Index: 4851182 (Open Web Text)

Max Activating Token Index: 461

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 15.3501. Min Range: -15.3501

Max Act: 15.1001. Min Act: -0.1700

Data Index: 818230 (Open Web Text)

Max Activating Token Index: 218

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 15.3501. Min Range: -15.3501

Max Act: 15.0376. Min Act: -0.1700

Data Index: 3825565 (Open Web Text)

Max Activating Token Index: 521

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 15.3501. Min Range: -15.3501

Max Act: 15.0376. Min Act: -0.1700

Data Index: 7132502 (Open Web Text)

Max Activating Token Index: 224

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 15.3501. Min Range: -15.3501

Max Act: 15.0376. Min Act: -0.1700

Data Index: 4663286 (Open Web Text)

Max Activating Token Index: 800

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 15.3501. Min Range: -15.3501

Max Act: 15.0376. Min Act: -0.1700

Data Index: 4569360 (Open Web Text)

Max Activating Token Index: 206

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 15.3501. Min Range: -15.3501

Max Act: 15.0376. Min Act: -0.1700

Data Index: 1866600 (Open Web Text)

Max Activating Token Index: 690

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 15.3501. Min Range: -15.3501

Max Act: 14.9126. Min Act: -0.1700

Data Index: 7001339 (Open Web Text)

Max Activating Token Index: 782

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 15.3501. Min Range: -15.3501

Max Act: 14.9751. Min Act: -0.1700

Data Index: 1634500 (Open Web Text)

Max Activating Token Index: 551

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 15.3501. Min Range: -15.3501

Max Act: 14.9751. Min Act: -0.1700

Data Index: 4541572 (Open Web Text)

Max Activating Token Index: 851

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 15.3501. Min Range: -15.3501

Max Act: 14.9751. Min Act: -0.1700

Data Index: 3706775 (Open Web Text)

Max Activating Token Index: 880

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 15.3501. Min Range: -15.3501

Max Act: 14.9126. Min Act: -0.1700

Data Index: 8479081 (Open Web Text)

Max Activating Token Index: 720

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 15.3501. Min Range: -15.3501

Max Act: 14.9126. Min Act: -0.1700

Data Index: 2217310 (Open Web Text)

Max Activating Token Index: 417

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 15.3501. Min Range: -15.3501

Max Act: 14.8501. Min Act: -0.1700

Data Index: 1329111 (Open Web Text)

Max Activating Token Index: 326

Click toggle to see full text

Truncated

Full Text #19