< Prev | Home | Model | Random | Next >

Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 249 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9532. Min Range: -2.9532

Max Act: 2.9532. Min Act: -0.1700

Data Index: 5434380 (Open Web Text)

Max Activating Token Index: 215

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.9532. Min Range: -2.9532

Max Act: 2.9394. Min Act: -0.1700

Data Index: 8359699 (Open Web Text)

Max Activating Token Index: 558

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.9532. Min Range: -2.9532

Max Act: 2.9028. Min Act: -0.1700

Data Index: 1546425 (Open Web Text)

Max Activating Token Index: 936

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.9532. Min Range: -2.9532

Max Act: 2.9209. Min Act: -0.1700

Data Index: 8551235 (Open Web Text)

Max Activating Token Index: 1022

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.9532. Min Range: -2.9532

Max Act: 2.8791. Min Act: -0.1700

Data Index: 774577 (Open Web Text)

Max Activating Token Index: 658

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.9532. Min Range: -2.9532

Max Act: 2.8736. Min Act: -0.1700

Data Index: 3620761 (Open Web Text)

Max Activating Token Index: 567

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.9532. Min Range: -2.9532

Max Act: 2.8458. Min Act: -0.1700

Data Index: 4087247 (Open Web Text)

Max Activating Token Index: 940

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.9532. Min Range: -2.9532

Max Act: 2.8735. Min Act: -0.1700

Data Index: 66311 (Open Web Text)

Max Activating Token Index: 459

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.9532. Min Range: -2.9532

Max Act: 2.8586. Min Act: -0.1700

Data Index: 1684387 (Open Web Text)

Max Activating Token Index: 977

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.9532. Min Range: -2.9532

Max Act: 2.8545. Min Act: -0.1700

Data Index: 8031595 (Open Web Text)

Max Activating Token Index: 946

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.9532. Min Range: -2.9532

Max Act: 2.8141. Min Act: -0.1700

Data Index: 7123595 (Open Web Text)

Max Activating Token Index: 207

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.9532. Min Range: -2.9532

Max Act: 2.8396. Min Act: -0.1700

Data Index: 140863 (Open Web Text)

Max Activating Token Index: 443

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.9532. Min Range: -2.9532

Max Act: 2.7956. Min Act: -0.1700

Data Index: 2243561 (Open Web Text)

Max Activating Token Index: 415

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.9532. Min Range: -2.9532

Max Act: 2.8180. Min Act: -0.1700

Data Index: 7750041 (Open Web Text)

Max Activating Token Index: 573

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.9532. Min Range: -2.9532

Max Act: 2.7975. Min Act: -0.1700

Data Index: 3540853 (Open Web Text)

Max Activating Token Index: 50

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.9532. Min Range: -2.9532

Max Act: 2.8112. Min Act: -0.1700

Data Index: 6707362 (Open Web Text)

Max Activating Token Index: 462

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.9532. Min Range: -2.9532

Max Act: 2.7859. Min Act: -0.1700

Data Index: 7334609 (Open Web Text)

Max Activating Token Index: 433

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.9532. Min Range: -2.9532

Max Act: 2.8119. Min Act: -0.1700

Data Index: 8023149 (Open Web Text)

Max Activating Token Index: 410

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.9532. Min Range: -2.9532

Max Act: 2.7563. Min Act: -0.1700

Data Index: 1655976 (Open Web Text)

Max Activating Token Index: 639

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.9532. Min Range: -2.9532

Max Act: 2.7743. Min Act: -0.1700

Data Index: 3360550 (Open Web Text)

Max Activating Token Index: 109

Click toggle to see full text

Truncated

Full Text #19