< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 6326 in Layer 47

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 10.3454. Min Range: -10.3454

Max Act: 10.3454. Min Act: -0.1700

Data Index: 2040914 (Open Web Text)

Max Activating Token Index: 712

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 10.3454. Min Range: -10.3454

Max Act: 9.6579. Min Act: -0.1700

Data Index: 6576245 (Open Web Text)

Max Activating Token Index: 536

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 10.3454. Min Range: -10.3454

Max Act: 9.5954. Min Act: -0.1700

Data Index: 3058738 (Open Web Text)

Max Activating Token Index: 285

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 10.3454. Min Range: -10.3454

Max Act: 9.5329. Min Act: -0.1700

Data Index: 4795571 (Open Web Text)

Max Activating Token Index: 928

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 10.3454. Min Range: -10.3454

Max Act: 9.5329. Min Act: -0.1700

Data Index: 4400518 (Open Web Text)

Max Activating Token Index: 92

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 10.3454. Min Range: -10.3454

Max Act: 9.4079. Min Act: -0.1700

Data Index: 3856336 (Open Web Text)

Max Activating Token Index: 283

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 10.3454. Min Range: -10.3454

Max Act: 9.4079. Min Act: -0.1700

Data Index: 916195 (Open Web Text)

Max Activating Token Index: 777

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 10.3454. Min Range: -10.3454

Max Act: 9.4704. Min Act: -0.1700

Data Index: 4795573 (Open Web Text)

Max Activating Token Index: 647

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 10.3454. Min Range: -10.3454

Max Act: 9.4704. Min Act: -0.1700

Data Index: 8411364 (Open Web Text)

Max Activating Token Index: 794

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 10.3454. Min Range: -10.3454

Max Act: 9.4079. Min Act: -0.1700

Data Index: 5932473 (Open Web Text)

Max Activating Token Index: 286

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 10.3454. Min Range: -10.3454

Max Act: 9.4079. Min Act: -0.1700

Data Index: 7651448 (Open Web Text)

Max Activating Token Index: 532

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 10.3454. Min Range: -10.3454

Max Act: 9.4704. Min Act: -0.1700

Data Index: 6419380 (Open Web Text)

Max Activating Token Index: 181

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 10.3454. Min Range: -10.3454

Max Act: 9.4079. Min Act: -0.1700

Data Index: 4054567 (Open Web Text)

Max Activating Token Index: 669

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 10.3454. Min Range: -10.3454

Max Act: 9.3454. Min Act: -0.1700

Data Index: 8491266 (Open Web Text)

Max Activating Token Index: 302

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 10.3454. Min Range: -10.3454

Max Act: 9.4079. Min Act: -0.1700

Data Index: 457091 (Open Web Text)

Max Activating Token Index: 281

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 10.3454. Min Range: -10.3454

Max Act: 9.3454. Min Act: -0.1700

Data Index: 2418248 (Open Web Text)

Max Activating Token Index: 112

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 10.3454. Min Range: -10.3454

Max Act: 9.2829. Min Act: -0.1700

Data Index: 2797390 (Open Web Text)

Max Activating Token Index: 55

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 10.3454. Min Range: -10.3454

Max Act: 9.3454. Min Act: -0.1700

Data Index: 5197836 (Open Web Text)

Max Activating Token Index: 862

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 10.3454. Min Range: -10.3454

Max Act: 9.2829. Min Act: -0.1700

Data Index: 1175432 (Open Web Text)

Max Activating Token Index: 403

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 10.3454. Min Range: -10.3454

Max Act: 9.2829. Min Act: -0.1700

Data Index: 8113965 (Open Web Text)

Max Activating Token Index: 1018

Click toggle to see full text

Truncated

Full Text #19