< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 6368 in Layer 41

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 8.0924. Min Range: -8.0924

Max Act: 8.0924. Min Act: -0.1700

Data Index: 2698073 (Open Web Text)

Max Activating Token Index: 380

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 8.0924. Min Range: -8.0924

Max Act: 7.7799. Min Act: -0.1700

Data Index: 373593 (Open Web Text)

Max Activating Token Index: 574

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 8.0924. Min Range: -8.0924

Max Act: 7.6862. Min Act: -0.1700

Data Index: 6026814 (Open Web Text)

Max Activating Token Index: 561

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 8.0924. Min Range: -8.0924

Max Act: 7.6237. Min Act: -0.1700

Data Index: 5451655 (Open Web Text)

Max Activating Token Index: 456

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 8.0924. Min Range: -8.0924

Max Act: 7.4362. Min Act: -0.1700

Data Index: 2218626 (Open Web Text)

Max Activating Token Index: 692

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 8.0924. Min Range: -8.0924

Max Act: 7.4049. Min Act: -0.1700

Data Index: 8729810 (Open Web Text)

Max Activating Token Index: 34

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 8.0924. Min Range: -8.0924

Max Act: 7.3424. Min Act: -0.1700

Data Index: 5451653 (Open Web Text)

Max Activating Token Index: 665

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 8.0924. Min Range: -8.0924

Max Act: 7.3424. Min Act: -0.1700

Data Index: 5148808 (Open Web Text)

Max Activating Token Index: 827

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 8.0924. Min Range: -8.0924

Max Act: 7.3112. Min Act: -0.1700

Data Index: 3438002 (Open Web Text)

Max Activating Token Index: 103

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 8.0924. Min Range: -8.0924

Max Act: 7.2799. Min Act: -0.1700

Data Index: 6135865 (Open Web Text)

Max Activating Token Index: 283

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 8.0924. Min Range: -8.0924

Max Act: 7.2174. Min Act: -0.1700

Data Index: 5507457 (Open Web Text)

Max Activating Token Index: 824

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 8.0924. Min Range: -8.0924

Max Act: 7.2174. Min Act: -0.1700

Data Index: 959881 (Open Web Text)

Max Activating Token Index: 651

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 8.0924. Min Range: -8.0924

Max Act: 7.1862. Min Act: -0.1700

Data Index: 2431962 (Open Web Text)

Max Activating Token Index: 714

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 8.0924. Min Range: -8.0924

Max Act: 7.2174. Min Act: -0.1700

Data Index: 4957867 (Open Web Text)

Max Activating Token Index: 834

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 8.0924. Min Range: -8.0924

Max Act: 7.1862. Min Act: -0.1700

Data Index: 1382898 (Open Web Text)

Max Activating Token Index: 225

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 8.0924. Min Range: -8.0924

Max Act: 7.1549. Min Act: -0.1700

Data Index: 2034519 (Open Web Text)

Max Activating Token Index: 144

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 8.0924. Min Range: -8.0924

Max Act: 7.1237. Min Act: -0.1700

Data Index: 7799854 (Open Web Text)

Max Activating Token Index: 978

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 8.0924. Min Range: -8.0924

Max Act: 7.1237. Min Act: -0.1700

Data Index: 3237661 (Open Web Text)

Max Activating Token Index: 604

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 8.0924. Min Range: -8.0924

Max Act: 7.1237. Min Act: -0.1700

Data Index: 4243566 (Open Web Text)

Max Activating Token Index: 247

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 8.0924. Min Range: -8.0924

Max Act: 7.1549. Min Act: -0.1700

Data Index: 8676349 (Open Web Text)

Max Activating Token Index: 706

Click toggle to see full text

Truncated

Full Text #19