< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 553 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: 2.3770. Min Range: -2.3770

Max Act: 2.3770. Min Act: -0.1700

Data Index: 2942038 (Open Web Text)

Max Activating Token Index: 750

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.3770. Min Range: -2.3770

Max Act: 2.3632. Min Act: -0.1700

Data Index: 1208679 (Open Web Text)

Max Activating Token Index: 485

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.3770. Min Range: -2.3770

Max Act: 2.3451. Min Act: -0.1700

Data Index: 6089146 (Open Web Text)

Max Activating Token Index: 351

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.3770. Min Range: -2.3770

Max Act: 2.3417. Min Act: -0.1700

Data Index: 5230605 (Open Web Text)

Max Activating Token Index: 510

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.3770. Min Range: -2.3770

Max Act: 2.3523. Min Act: -0.1700

Data Index: 2507580 (Open Web Text)

Max Activating Token Index: 95

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.3770. Min Range: -2.3770

Max Act: 2.3496. Min Act: -0.1700

Data Index: 4104320 (Open Web Text)

Max Activating Token Index: 463

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.3770. Min Range: -2.3770

Max Act: 2.3590. Min Act: -0.1700

Data Index: 1183452 (Open Web Text)

Max Activating Token Index: 847

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.3770. Min Range: -2.3770

Max Act: 2.3432. Min Act: -0.1700

Data Index: 7189457 (Open Web Text)

Max Activating Token Index: 496

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.3770. Min Range: -2.3770

Max Act: 2.3294. Min Act: -0.1700

Data Index: 5115608 (Open Web Text)

Max Activating Token Index: 530

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.3770. Min Range: -2.3770

Max Act: 2.3408. Min Act: -0.1700

Data Index: 7528733 (Open Web Text)

Max Activating Token Index: 178

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.3770. Min Range: -2.3770

Max Act: 2.2623. Min Act: -0.1700

Data Index: 8309343 (Open Web Text)

Max Activating Token Index: 553

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.3770. Min Range: -2.3770

Max Act: 2.3018. Min Act: -0.1700

Data Index: 254386 (Open Web Text)

Max Activating Token Index: 667

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.3770. Min Range: -2.3770

Max Act: 2.3305. Min Act: -0.1700

Data Index: 457241 (Open Web Text)

Max Activating Token Index: 586

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.3770. Min Range: -2.3770

Max Act: 2.3063. Min Act: -0.1700

Data Index: 4649491 (Open Web Text)

Max Activating Token Index: 162

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.3770. Min Range: -2.3770

Max Act: 2.3021. Min Act: -0.1700

Data Index: 3121762 (Open Web Text)

Max Activating Token Index: 847

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.3770. Min Range: -2.3770

Max Act: 2.3054. Min Act: -0.1700

Data Index: 4469425 (Open Web Text)

Max Activating Token Index: 134

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.3770. Min Range: -2.3770

Max Act: 2.2750. Min Act: -0.1700

Data Index: 1195893 (Open Web Text)

Max Activating Token Index: 145

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.3770. Min Range: -2.3770

Max Act: 2.2875. Min Act: -0.1700

Data Index: 6329461 (Open Web Text)

Max Activating Token Index: 535

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.3770. Min Range: -2.3770

Max Act: 2.2861. Min Act: -0.1700

Data Index: 1197835 (Open Web Text)

Max Activating Token Index: 721

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.3770. Min Range: -2.3770

Max Act: 2.2826. Min Act: -0.1700

Data Index: 6688479 (Open Web Text)

Max Activating Token Index: 904

Click toggle to see full text

Truncated

Full Text #19