< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 2823 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.9486. Min Range: -2.9486

Max Act: 2.9486. Min Act: -0.1700

Data Index: 5563972 (Open Web Text)

Max Activating Token Index: 453

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.9486. Min Range: -2.9486

Max Act: 2.9149. Min Act: -0.1700

Data Index: 5471283 (Open Web Text)

Max Activating Token Index: 786

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.9486. Min Range: -2.9486

Max Act: 2.9366. Min Act: -0.1700

Data Index: 2477641 (Open Web Text)

Max Activating Token Index: 892

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.9486. Min Range: -2.9486

Max Act: 2.8559. Min Act: -0.1700

Data Index: 3005606 (Open Web Text)

Max Activating Token Index: 789

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.9486. Min Range: -2.9486

Max Act: 2.8260. Min Act: -0.1700

Data Index: 1374005 (Open Web Text)

Max Activating Token Index: 76

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.9486. Min Range: -2.9486

Max Act: 2.8385. Min Act: -0.1700

Data Index: 4214258 (Open Web Text)

Max Activating Token Index: 255

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.9486. Min Range: -2.9486

Max Act: 2.8023. Min Act: -0.1700

Data Index: 428389 (Open Web Text)

Max Activating Token Index: 362

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.9486. Min Range: -2.9486

Max Act: 2.7852. Min Act: -0.1700

Data Index: 1639893 (Open Web Text)

Max Activating Token Index: 347

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.9486. Min Range: -2.9486

Max Act: 2.7953. Min Act: -0.1700

Data Index: 4768099 (Open Web Text)

Max Activating Token Index: 526

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.9486. Min Range: -2.9486

Max Act: 2.7586. Min Act: -0.1700

Data Index: 2062307 (Open Web Text)

Max Activating Token Index: 477

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.9486. Min Range: -2.9486

Max Act: 2.7799. Min Act: -0.1700

Data Index: 4498145 (Open Web Text)

Max Activating Token Index: 935

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.9486. Min Range: -2.9486

Max Act: 2.7790. Min Act: -0.1700

Data Index: 4018152 (Open Web Text)

Max Activating Token Index: 200

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.9486. Min Range: -2.9486

Max Act: 2.7684. Min Act: -0.1700

Data Index: 4107311 (Open Web Text)

Max Activating Token Index: 766

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.9486. Min Range: -2.9486

Max Act: 2.7611. Min Act: -0.1700

Data Index: 5967701 (Open Web Text)

Max Activating Token Index: 424

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.9486. Min Range: -2.9486

Max Act: 2.7758. Min Act: -0.1700

Data Index: 6689195 (Open Web Text)

Max Activating Token Index: 230

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.9486. Min Range: -2.9486

Max Act: 2.7669. Min Act: -0.1700

Data Index: 4839274 (Open Web Text)

Max Activating Token Index: 721

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.9486. Min Range: -2.9486

Max Act: 2.7679. Min Act: -0.1700

Data Index: 3648572 (Open Web Text)

Max Activating Token Index: 557

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.9486. Min Range: -2.9486

Max Act: 2.7525. Min Act: -0.1700

Data Index: 1275267 (Open Web Text)

Max Activating Token Index: 874

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.9486. Min Range: -2.9486

Max Act: 2.7483. Min Act: -0.1700

Data Index: 5377807 (Open Web Text)

Max Activating Token Index: 951

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.9486. Min Range: -2.9486

Max Act: 2.7275. Min Act: -0.1700

Data Index: 2431957 (Open Web Text)

Max Activating Token Index: 832

Click toggle to see full text

Truncated

Full Text #19