< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 1207 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: 3.0710. Min Range: -3.0710

Max Act: 3.0710. Min Act: -0.1700

Data Index: 685525 (Open Web Text)

Max Activating Token Index: 599

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 3.0710. Min Range: -3.0710

Max Act: 2.9690. Min Act: -0.1700

Data Index: 4189841 (Open Web Text)

Max Activating Token Index: 225

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 3.0710. Min Range: -3.0710

Max Act: 2.9393. Min Act: -0.1700

Data Index: 189471 (Open Web Text)

Max Activating Token Index: 585

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 3.0710. Min Range: -3.0710

Max Act: 2.7974. Min Act: -0.1700

Data Index: 4694063 (Open Web Text)

Max Activating Token Index: 892

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 3.0710. Min Range: -3.0710

Max Act: 2.7094. Min Act: -0.1700

Data Index: 3877411 (Open Web Text)

Max Activating Token Index: 325

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 3.0710. Min Range: -3.0710

Max Act: 2.7112. Min Act: -0.1700

Data Index: 2869645 (Open Web Text)

Max Activating Token Index: 282

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 3.0710. Min Range: -3.0710

Max Act: 2.6575. Min Act: -0.1700

Data Index: 6823242 (Open Web Text)

Max Activating Token Index: 811

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 3.0710. Min Range: -3.0710

Max Act: 2.6444. Min Act: -0.1700

Data Index: 2902333 (Open Web Text)

Max Activating Token Index: 473

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 3.0710. Min Range: -3.0710

Max Act: 2.6317. Min Act: -0.1700

Data Index: 189472 (Open Web Text)

Max Activating Token Index: 611

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 3.0710. Min Range: -3.0710

Max Act: 2.6114. Min Act: -0.1700

Data Index: 737100 (Open Web Text)

Max Activating Token Index: 170

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 3.0710. Min Range: -3.0710

Max Act: 2.5781. Min Act: -0.1700

Data Index: 2732310 (Open Web Text)

Max Activating Token Index: 974

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 3.0710. Min Range: -3.0710

Max Act: 2.5488. Min Act: -0.1700

Data Index: 4608198 (Open Web Text)

Max Activating Token Index: 1009

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 3.0710. Min Range: -3.0710

Max Act: 2.5459. Min Act: -0.1700

Data Index: 5531554 (Open Web Text)

Max Activating Token Index: 746

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 3.0710. Min Range: -3.0710

Max Act: 2.5524. Min Act: -0.1700

Data Index: 6797421 (Open Web Text)

Max Activating Token Index: 332

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 3.0710. Min Range: -3.0710

Max Act: 2.5816. Min Act: -0.1700

Data Index: 3526819 (Open Web Text)

Max Activating Token Index: 526

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 3.0710. Min Range: -3.0710

Max Act: 2.5483. Min Act: -0.1700

Data Index: 502808 (Open Web Text)

Max Activating Token Index: 863

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 3.0710. Min Range: -3.0710

Max Act: 2.5372. Min Act: -0.1700

Data Index: 2284567 (Open Web Text)

Max Activating Token Index: 875

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 3.0710. Min Range: -3.0710

Max Act: 2.5351. Min Act: -0.1700

Data Index: 5035093 (Open Web Text)

Max Activating Token Index: 73

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 3.0710. Min Range: -3.0710

Max Act: 2.5376. Min Act: -0.1700

Data Index: 4792410 (Open Web Text)

Max Activating Token Index: 860

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 3.0710. Min Range: -3.0710

Max Act: 2.5310. Min Act: -0.1700

Data Index: 3648587 (Open Web Text)

Max Activating Token Index: 534

Click toggle to see full text

Truncated

Full Text #19