< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 483 in Layer 5

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: 2.6203. Min Range: -2.6203

Max Act: 2.6203. Min Act: -0.1700

Data Index: 4390911 (Open Web Text)

Max Activating Token Index: 988

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.6203. Min Range: -2.6203

Max Act: 2.6168. Min Act: -0.1700

Data Index: 7898346 (Open Web Text)

Max Activating Token Index: 755

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.6203. Min Range: -2.6203

Max Act: 2.6068. Min Act: -0.1700

Data Index: 7165671 (Open Web Text)

Max Activating Token Index: 509

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.6203. Min Range: -2.6203

Max Act: 2.5860. Min Act: -0.1700

Data Index: 4819166 (Open Web Text)

Max Activating Token Index: 407

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.6203. Min Range: -2.6203

Max Act: 2.5694. Min Act: -0.1700

Data Index: 4731841 (Open Web Text)

Max Activating Token Index: 928

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.6203. Min Range: -2.6203

Max Act: 2.5506. Min Act: -0.1700

Data Index: 4596088 (Open Web Text)

Max Activating Token Index: 434

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.6203. Min Range: -2.6203

Max Act: 2.5531. Min Act: -0.1700

Data Index: 1101234 (Open Web Text)

Max Activating Token Index: 550

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.6203. Min Range: -2.6203

Max Act: 2.5571. Min Act: -0.1700

Data Index: 453278 (Open Web Text)

Max Activating Token Index: 951

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.6203. Min Range: -2.6203

Max Act: 2.5275. Min Act: -0.1700

Data Index: 1817617 (Open Web Text)

Max Activating Token Index: 663

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.6203. Min Range: -2.6203

Max Act: 2.5120. Min Act: -0.1700

Data Index: 1943402 (Open Web Text)

Max Activating Token Index: 627

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.6203. Min Range: -2.6203

Max Act: 2.5109. Min Act: -0.1700

Data Index: 2800085 (Open Web Text)

Max Activating Token Index: 558

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.6203. Min Range: -2.6203

Max Act: 2.5094. Min Act: -0.1700

Data Index: 6902617 (Open Web Text)

Max Activating Token Index: 446

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.6203. Min Range: -2.6203

Max Act: 2.4918. Min Act: -0.1700

Data Index: 5613343 (Open Web Text)

Max Activating Token Index: 217

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.6203. Min Range: -2.6203

Max Act: 2.4974. Min Act: -0.1700

Data Index: 7586622 (Open Web Text)

Max Activating Token Index: 483

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.6203. Min Range: -2.6203

Max Act: 2.5063. Min Act: -0.1700

Data Index: 5176192 (Open Web Text)

Max Activating Token Index: 437

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.6203. Min Range: -2.6203

Max Act: 2.5082. Min Act: -0.1700

Data Index: 4832268 (Open Web Text)

Max Activating Token Index: 763

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.6203. Min Range: -2.6203

Max Act: 2.4969. Min Act: -0.1700

Data Index: 3774469 (Open Web Text)

Max Activating Token Index: 307

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.6203. Min Range: -2.6203

Max Act: 2.5014. Min Act: -0.1700

Data Index: 3430305 (Open Web Text)

Max Activating Token Index: 510

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.6203. Min Range: -2.6203

Max Act: 2.4804. Min Act: -0.1700

Data Index: 1385777 (Open Web Text)

Max Activating Token Index: 978

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.6203. Min Range: -2.6203

Max Act: 2.4985. Min Act: -0.1700

Data Index: 1969356 (Open Web Text)

Max Activating Token Index: 525

Click toggle to see full text

Truncated

Full Text #19