< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 1876 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: 4.5688. Min Range: -4.5688

Max Act: 4.5688. Min Act: -0.1700

Data Index: 4877001 (Open Web Text)

Max Activating Token Index: 595

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 4.5688. Min Range: -4.5688

Max Act: 4.3988. Min Act: -0.1700

Data Index: 6930296 (Open Web Text)

Max Activating Token Index: 717

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 4.5688. Min Range: -4.5688

Max Act: 4.2652. Min Act: -0.1700

Data Index: 8594230 (Open Web Text)

Max Activating Token Index: 356

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 4.5688. Min Range: -4.5688

Max Act: 4.2188. Min Act: -0.1700

Data Index: 4542067 (Open Web Text)

Max Activating Token Index: 203

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 4.5688. Min Range: -4.5688

Max Act: 4.1554. Min Act: -0.1700

Data Index: 6801162 (Open Web Text)

Max Activating Token Index: 516

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 4.5688. Min Range: -4.5688

Max Act: 4.1656. Min Act: -0.1700

Data Index: 3110965 (Open Web Text)

Max Activating Token Index: 466

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 4.5688. Min Range: -4.5688

Max Act: 4.1575. Min Act: -0.1700

Data Index: 2806906 (Open Web Text)

Max Activating Token Index: 574

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 4.5688. Min Range: -4.5688

Max Act: 4.1504. Min Act: -0.1700

Data Index: 2436059 (Open Web Text)

Max Activating Token Index: 296

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 4.5688. Min Range: -4.5688

Max Act: 4.1282. Min Act: -0.1700

Data Index: 8619403 (Open Web Text)

Max Activating Token Index: 537

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 4.5688. Min Range: -4.5688

Max Act: 4.1220. Min Act: -0.1700

Data Index: 4479011 (Open Web Text)

Max Activating Token Index: 561

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 4.5688. Min Range: -4.5688

Max Act: 4.1112. Min Act: -0.1700

Data Index: 6254533 (Open Web Text)

Max Activating Token Index: 248

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 4.5688. Min Range: -4.5688

Max Act: 4.1015. Min Act: -0.1700

Data Index: 6628377 (Open Web Text)

Max Activating Token Index: 731

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 4.5688. Min Range: -4.5688

Max Act: 4.0819. Min Act: -0.1700

Data Index: 160330 (Open Web Text)

Max Activating Token Index: 823

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 4.5688. Min Range: -4.5688

Max Act: 4.0576. Min Act: -0.1700

Data Index: 7634942 (Open Web Text)

Max Activating Token Index: 522

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 4.5688. Min Range: -4.5688

Max Act: 4.0635. Min Act: -0.1700

Data Index: 1748722 (Open Web Text)

Max Activating Token Index: 817

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 4.5688. Min Range: -4.5688

Max Act: 4.0829. Min Act: -0.1700

Data Index: 2718760 (Open Web Text)

Max Activating Token Index: 954

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 4.5688. Min Range: -4.5688

Max Act: 4.0763. Min Act: -0.1700

Data Index: 8557970 (Open Web Text)

Max Activating Token Index: 279

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 4.5688. Min Range: -4.5688

Max Act: 4.0829. Min Act: -0.1700

Data Index: 7320717 (Open Web Text)

Max Activating Token Index: 896

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 4.5688. Min Range: -4.5688

Max Act: 4.0760. Min Act: -0.1700

Data Index: 3425920 (Open Web Text)

Max Activating Token Index: 404

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 4.5688. Min Range: -4.5688

Max Act: 4.0706. Min Act: -0.1700

Data Index: 3005846 (Open Web Text)

Max Activating Token Index: 604

Click toggle to see full text

Truncated

Full Text #19