< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 4 in Layer 34

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 10.8404. Min Range: -10.8404

Max Act: 10.8404. Min Act: -0.1700

Data Index: 4885172 (Open Web Text)

Max Activating Token Index: 827

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 10.8404. Min Range: -10.8404

Max Act: 10.7779. Min Act: -0.1700

Data Index: 98132 (Open Web Text)

Max Activating Token Index: 652

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 10.8404. Min Range: -10.8404

Max Act: 10.6529. Min Act: -0.1700

Data Index: 1955272 (Open Web Text)

Max Activating Token Index: 184

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 10.8404. Min Range: -10.8404

Max Act: 10.5279. Min Act: -0.1700

Data Index: 1753386 (Open Web Text)

Max Activating Token Index: 333

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 10.8404. Min Range: -10.8404

Max Act: 10.4029. Min Act: -0.1700

Data Index: 319311 (Open Web Text)

Max Activating Token Index: 800

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 10.8404. Min Range: -10.8404

Max Act: 10.4029. Min Act: -0.1700

Data Index: 4643936 (Open Web Text)

Max Activating Token Index: 156

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 10.8404. Min Range: -10.8404

Max Act: 10.3404. Min Act: -0.1700

Data Index: 4843054 (Open Web Text)

Max Activating Token Index: 677

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 10.8404. Min Range: -10.8404

Max Act: 10.2779. Min Act: -0.1700

Data Index: 4467486 (Open Web Text)

Max Activating Token Index: 677

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 10.8404. Min Range: -10.8404

Max Act: 10.3404. Min Act: -0.1700

Data Index: 6841331 (Open Web Text)

Max Activating Token Index: 179

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 10.8404. Min Range: -10.8404

Max Act: 10.3404. Min Act: -0.1700

Data Index: 5589231 (Open Web Text)

Max Activating Token Index: 928

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 10.8404. Min Range: -10.8404

Max Act: 10.2779. Min Act: -0.1700

Data Index: 1643920 (Open Web Text)

Max Activating Token Index: 445

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 10.8404. Min Range: -10.8404

Max Act: 10.2154. Min Act: -0.1700

Data Index: 6532401 (Open Web Text)

Max Activating Token Index: 726

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 10.8404. Min Range: -10.8404

Max Act: 10.2154. Min Act: -0.1700

Data Index: 6930850 (Open Web Text)

Max Activating Token Index: 264

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 10.8404. Min Range: -10.8404

Max Act: 10.0904. Min Act: -0.1700

Data Index: 4499108 (Open Web Text)

Max Activating Token Index: 467

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 10.8404. Min Range: -10.8404

Max Act: 10.1529. Min Act: -0.1700

Data Index: 7444732 (Open Web Text)

Max Activating Token Index: 971

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 10.8404. Min Range: -10.8404

Max Act: 10.0904. Min Act: -0.1700

Data Index: 3438511 (Open Web Text)

Max Activating Token Index: 807

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 10.8404. Min Range: -10.8404

Max Act: 10.0904. Min Act: -0.1700

Data Index: 6007235 (Open Web Text)

Max Activating Token Index: 818

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 10.8404. Min Range: -10.8404

Max Act: 10.0279. Min Act: -0.1700

Data Index: 6074085 (Open Web Text)

Max Activating Token Index: 888

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 10.8404. Min Range: -10.8404

Max Act: 9.9654. Min Act: -0.1700

Data Index: 7754382 (Open Web Text)

Max Activating Token Index: 301

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 10.8404. Min Range: -10.8404

Max Act: 9.9029. Min Act: -0.1700

Data Index: 4343569 (Open Web Text)

Max Activating Token Index: 462

Click toggle to see full text

Truncated

Full Text #19