< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 1815 in Layer 3

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: 2.7862. Min Range: -2.7862

Max Act: 2.7862. Min Act: -0.1700

Data Index: 7112254 (Open Web Text)

Max Activating Token Index: 745

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.7862. Min Range: -2.7862

Max Act: 2.7523. Min Act: -0.1700

Data Index: 5972599 (Open Web Text)

Max Activating Token Index: 354

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.7862. Min Range: -2.7862

Max Act: 2.7392. Min Act: -0.1700

Data Index: 4485806 (Open Web Text)

Max Activating Token Index: 384

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.7862. Min Range: -2.7862

Max Act: 2.7535. Min Act: -0.1700

Data Index: 1486788 (Open Web Text)

Max Activating Token Index: 135

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.7862. Min Range: -2.7862

Max Act: 2.7172. Min Act: -0.1700

Data Index: 8443674 (Open Web Text)

Max Activating Token Index: 467

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.7862. Min Range: -2.7862

Max Act: 2.7202. Min Act: -0.1700

Data Index: 6241203 (Open Web Text)

Max Activating Token Index: 634

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.7862. Min Range: -2.7862

Max Act: 2.7041. Min Act: -0.1700

Data Index: 2557452 (Open Web Text)

Max Activating Token Index: 875

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.7862. Min Range: -2.7862

Max Act: 2.7088. Min Act: -0.1700

Data Index: 4214923 (Open Web Text)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.7862. Min Range: -2.7862

Max Act: 2.6871. Min Act: -0.1700

Data Index: 306503 (Open Web Text)

Max Activating Token Index: 9

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.7862. Min Range: -2.7862

Max Act: 2.7001. Min Act: -0.1700

Data Index: 7898987 (Open Web Text)

Max Activating Token Index: 43

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.7862. Min Range: -2.7862

Max Act: 2.6638. Min Act: -0.1700

Data Index: 1650663 (Open Web Text)

Max Activating Token Index: 728

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.7862. Min Range: -2.7862

Max Act: 2.6518. Min Act: -0.1700

Data Index: 912876 (Open Web Text)

Max Activating Token Index: 504

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.7862. Min Range: -2.7862

Max Act: 2.6778. Min Act: -0.1700

Data Index: 5882320 (Open Web Text)

Max Activating Token Index: 224

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.7862. Min Range: -2.7862

Max Act: 2.6487. Min Act: -0.1700

Data Index: 1749820 (Open Web Text)

Max Activating Token Index: 465

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.7862. Min Range: -2.7862

Max Act: 2.6414. Min Act: -0.1700

Data Index: 6173678 (Open Web Text)

Max Activating Token Index: 244

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.7862. Min Range: -2.7862

Max Act: 2.6442. Min Act: -0.1700

Data Index: 7509103 (Open Web Text)

Max Activating Token Index: 425

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.7862. Min Range: -2.7862

Max Act: 2.6504. Min Act: -0.1700

Data Index: 8819393 (Open Web Text)

Max Activating Token Index: 935

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.7862. Min Range: -2.7862

Max Act: 2.6367. Min Act: -0.1700

Data Index: 3802021 (Open Web Text)

Max Activating Token Index: 501

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.7862. Min Range: -2.7862

Max Act: 2.6209. Min Act: -0.1700

Data Index: 5176746 (Open Web Text)

Max Activating Token Index: 559

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.7862. Min Range: -2.7862

Max Act: 2.6626. Min Act: -0.1700

Data Index: 6074446 (Open Web Text)

Max Activating Token Index: 571

Click toggle to see full text

Truncated

Full Text #19