< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 105 in Layer 0

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: 2.9393. Min Range: -2.9393

Max Act: 2.9393. Min Act: -0.1700

Data Index: 4509066 (Open Web Text)

Max Activating Token Index: 42

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.9393. Min Range: -2.9393

Max Act: 2.9319. Min Act: -0.1700

Data Index: 5729009 (Open Web Text)

Max Activating Token Index: 709

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.9393. Min Range: -2.9393

Max Act: 2.9368. Min Act: -0.1700

Data Index: 7672132 (Open Web Text)

Max Activating Token Index: 962

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.9393. Min Range: -2.9393

Max Act: 2.9197. Min Act: -0.1700

Data Index: 3836136 (Open Web Text)

Max Activating Token Index: 526

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.9393. Min Range: -2.9393

Max Act: 2.9068. Min Act: -0.1700

Data Index: 5365432 (Open Web Text)

Max Activating Token Index: 922

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.9393. Min Range: -2.9393

Max Act: 2.9029. Min Act: -0.1700

Data Index: 2553181 (Open Web Text)

Max Activating Token Index: 1005

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.9393. Min Range: -2.9393

Max Act: 2.8974. Min Act: -0.1700

Data Index: 6695689 (Open Web Text)

Max Activating Token Index: 9

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.9393. Min Range: -2.9393

Max Act: 2.8913. Min Act: -0.1700

Data Index: 1720139 (Open Web Text)

Max Activating Token Index: 857

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.9393. Min Range: -2.9393

Max Act: 2.8920. Min Act: -0.1700

Data Index: 7842790 (Open Web Text)

Max Activating Token Index: 523

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.9393. Min Range: -2.9393

Max Act: 2.8873. Min Act: -0.1700

Data Index: 7846252 (Open Web Text)

Max Activating Token Index: 107

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.9393. Min Range: -2.9393

Max Act: 2.8815. Min Act: -0.1700

Data Index: 7943422 (Open Web Text)

Max Activating Token Index: 474

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.9393. Min Range: -2.9393

Max Act: 2.8683. Min Act: -0.1700

Data Index: 3952011 (Open Web Text)

Max Activating Token Index: 877

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.9393. Min Range: -2.9393

Max Act: 2.8751. Min Act: -0.1700

Data Index: 4005608 (Open Web Text)

Max Activating Token Index: 739

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.9393. Min Range: -2.9393

Max Act: 2.8747. Min Act: -0.1700

Data Index: 3657885 (Open Web Text)

Max Activating Token Index: 663

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.9393. Min Range: -2.9393

Max Act: 2.8670. Min Act: -0.1700

Data Index: 8545238 (Open Web Text)

Max Activating Token Index: 259

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.9393. Min Range: -2.9393

Max Act: 2.8725. Min Act: -0.1700

Data Index: 2396918 (Open Web Text)

Max Activating Token Index: 794

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.9393. Min Range: -2.9393

Max Act: 2.8714. Min Act: -0.1700

Data Index: 629809 (Open Web Text)

Max Activating Token Index: 455

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.9393. Min Range: -2.9393

Max Act: 2.8690. Min Act: -0.1700

Data Index: 4499544 (Open Web Text)

Max Activating Token Index: 675

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.9393. Min Range: -2.9393

Max Act: 2.8710. Min Act: -0.1700

Data Index: 5727454 (Open Web Text)

Max Activating Token Index: 264

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.9393. Min Range: -2.9393

Max Act: 2.8642. Min Act: -0.1700

Data Index: 2574200 (Open Web Text)

Max Activating Token Index: 432

Click toggle to see full text

Truncated

Full Text #19