< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 514 in Layer 5

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: 2.5002. Min Range: -2.5002

Max Act: 2.5002. Min Act: -0.1700

Data Index: 5976328 (Open Web Text)

Max Activating Token Index: 859

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.5002. Min Range: -2.5002

Max Act: 2.4384. Min Act: -0.1700

Data Index: 3911602 (Open Web Text)

Max Activating Token Index: 165

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.5002. Min Range: -2.5002

Max Act: 2.4248. Min Act: -0.1700

Data Index: 274750 (Open Web Text)

Max Activating Token Index: 842

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.5002. Min Range: -2.5002

Max Act: 2.4014. Min Act: -0.1700

Data Index: 344025 (Open Web Text)

Max Activating Token Index: 906

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.5002. Min Range: -2.5002

Max Act: 2.3870. Min Act: -0.1700

Data Index: 3791681 (Open Web Text)

Max Activating Token Index: 254

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.5002. Min Range: -2.5002

Max Act: 2.3847. Min Act: -0.1700

Data Index: 2827482 (Open Web Text)

Max Activating Token Index: 225

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.5002. Min Range: -2.5002

Max Act: 2.3852. Min Act: -0.1700

Data Index: 1371088 (Open Web Text)

Max Activating Token Index: 429

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.5002. Min Range: -2.5002

Max Act: 2.3781. Min Act: -0.1700

Data Index: 615638 (Open Web Text)

Max Activating Token Index: 948

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.5002. Min Range: -2.5002

Max Act: 2.3652. Min Act: -0.1700

Data Index: 8450699 (Open Web Text)

Max Activating Token Index: 788

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.5002. Min Range: -2.5002

Max Act: 2.3627. Min Act: -0.1700

Data Index: 7715264 (Open Web Text)

Max Activating Token Index: 817

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.5002. Min Range: -2.5002

Max Act: 2.3704. Min Act: -0.1700

Data Index: 3606871 (Open Web Text)

Max Activating Token Index: 253

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.5002. Min Range: -2.5002

Max Act: 2.3507. Min Act: -0.1700

Data Index: 8681437 (Open Web Text)

Max Activating Token Index: 946

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.5002. Min Range: -2.5002

Max Act: 2.3339. Min Act: -0.1700

Data Index: 3835392 (Open Web Text)

Max Activating Token Index: 635

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.5002. Min Range: -2.5002

Max Act: 2.3503. Min Act: -0.1700

Data Index: 2652528 (Open Web Text)

Max Activating Token Index: 882

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.5002. Min Range: -2.5002

Max Act: 2.3487. Min Act: -0.1700

Data Index: 5012507 (Open Web Text)

Max Activating Token Index: 425

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.5002. Min Range: -2.5002

Max Act: 2.3176. Min Act: -0.1700

Data Index: 5728721 (Open Web Text)

Max Activating Token Index: 656

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.5002. Min Range: -2.5002

Max Act: 2.3387. Min Act: -0.1700

Data Index: 3436840 (Open Web Text)

Max Activating Token Index: 778

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.5002. Min Range: -2.5002

Max Act: 2.3287. Min Act: -0.1700

Data Index: 4299313 (Open Web Text)

Max Activating Token Index: 421

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.5002. Min Range: -2.5002

Max Act: 2.3357. Min Act: -0.1700

Data Index: 4306831 (Open Web Text)

Max Activating Token Index: 908

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.5002. Min Range: -2.5002

Max Act: 2.3290. Min Act: -0.1700

Data Index: 4433530 (Open Web Text)

Max Activating Token Index: 554

Click toggle to see full text

Truncated

Full Text #19