< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 2373 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: 2.9396. Min Range: -2.9396

Max Act: 2.9396. Min Act: -0.1700

Data Index: 2685643 (Open Web Text)

Max Activating Token Index: 57

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.9396. Min Range: -2.9396

Max Act: 2.8736. Min Act: -0.1700

Data Index: 3413253 (Open Web Text)

Max Activating Token Index: 790

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.9396. Min Range: -2.9396

Max Act: 2.8613. Min Act: -0.1700

Data Index: 2112263 (Open Web Text)

Max Activating Token Index: 518

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.9396. Min Range: -2.9396

Max Act: 2.7974. Min Act: -0.1700

Data Index: 2685670 (Open Web Text)

Max Activating Token Index: 313

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.9396. Min Range: -2.9396

Max Act: 2.7776. Min Act: -0.1700

Data Index: 3750734 (Open Web Text)

Max Activating Token Index: 643

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.9396. Min Range: -2.9396

Max Act: 2.7633. Min Act: -0.1700

Data Index: 2685644 (Open Web Text)

Max Activating Token Index: 165

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.9396. Min Range: -2.9396

Max Act: 2.7645. Min Act: -0.1700

Data Index: 4907242 (Open Web Text)

Max Activating Token Index: 1004

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.9396. Min Range: -2.9396

Max Act: 2.7545. Min Act: -0.1700

Data Index: 5093400 (Open Web Text)

Max Activating Token Index: 310

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.9396. Min Range: -2.9396

Max Act: 2.7369. Min Act: -0.1700

Data Index: 1100394 (Open Web Text)

Max Activating Token Index: 1006

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.9396. Min Range: -2.9396

Max Act: 2.7430. Min Act: -0.1700

Data Index: 5707264 (Open Web Text)

Max Activating Token Index: 81

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.9396. Min Range: -2.9396

Max Act: 2.7147. Min Act: -0.1700

Data Index: 2885027 (Open Web Text)

Max Activating Token Index: 874

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.9396. Min Range: -2.9396

Max Act: 2.6831. Min Act: -0.1700

Data Index: 2931655 (Open Web Text)

Max Activating Token Index: 305

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.9396. Min Range: -2.9396

Max Act: 2.6699. Min Act: -0.1700

Data Index: 1100393 (Open Web Text)

Max Activating Token Index: 592

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.9396. Min Range: -2.9396

Max Act: 2.6894. Min Act: -0.1700

Data Index: 5643649 (Open Web Text)

Max Activating Token Index: 414

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.9396. Min Range: -2.9396

Max Act: 2.6993. Min Act: -0.1700

Data Index: 2728766 (Open Web Text)

Max Activating Token Index: 758

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.9396. Min Range: -2.9396

Max Act: 2.6865. Min Act: -0.1700

Data Index: 4276943 (Open Web Text)

Max Activating Token Index: 368

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.9396. Min Range: -2.9396

Max Act: 2.6726. Min Act: -0.1700

Data Index: 4436993 (Open Web Text)

Max Activating Token Index: 563

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.9396. Min Range: -2.9396

Max Act: 2.6696. Min Act: -0.1700

Data Index: 4749530 (Open Web Text)

Max Activating Token Index: 114

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.9396. Min Range: -2.9396

Max Act: 2.6766. Min Act: -0.1700

Data Index: 2672123 (Open Web Text)

Max Activating Token Index: 897

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.9396. Min Range: -2.9396

Max Act: 2.6734. Min Act: -0.1700

Data Index: 4642176 (Open Web Text)

Max Activating Token Index: 869

Click toggle to see full text

Truncated

Full Text #19