< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 2027 in Layer 4

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: 2.7271. Min Range: -2.7271

Max Act: 2.7271. Min Act: -0.1700

Data Index: 2716142 (Open Web Text)

Max Activating Token Index: 600

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.7271. Min Range: -2.7271

Max Act: 2.6856. Min Act: -0.1700

Data Index: 3349879 (Open Web Text)

Max Activating Token Index: 764

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.7271. Min Range: -2.7271

Max Act: 2.6839. Min Act: -0.1700

Data Index: 590195 (Open Web Text)

Max Activating Token Index: 623

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.7271. Min Range: -2.7271

Max Act: 2.6560. Min Act: -0.1700

Data Index: 6705662 (Open Web Text)

Max Activating Token Index: 607

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.7271. Min Range: -2.7271

Max Act: 2.6612. Min Act: -0.1700

Data Index: 3929056 (Open Web Text)

Max Activating Token Index: 791

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.7271. Min Range: -2.7271

Max Act: 2.6364. Min Act: -0.1700

Data Index: 4175705 (Open Web Text)

Max Activating Token Index: 327

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.7271. Min Range: -2.7271

Max Act: 2.6222. Min Act: -0.1700

Data Index: 2966123 (Open Web Text)

Max Activating Token Index: 872

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.7271. Min Range: -2.7271

Max Act: 2.6424. Min Act: -0.1700

Data Index: 6897442 (Open Web Text)

Max Activating Token Index: 287

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.7271. Min Range: -2.7271

Max Act: 2.6191. Min Act: -0.1700

Data Index: 7071281 (Open Web Text)

Max Activating Token Index: 594

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.7271. Min Range: -2.7271

Max Act: 2.6575. Min Act: -0.1700

Data Index: 1966000 (Open Web Text)

Max Activating Token Index: 681

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.7271. Min Range: -2.7271

Max Act: 2.6268. Min Act: -0.1700

Data Index: 4822244 (Open Web Text)

Max Activating Token Index: 572

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.7271. Min Range: -2.7271

Max Act: 2.5895. Min Act: -0.1700

Data Index: 2785031 (Open Web Text)

Max Activating Token Index: 423

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.7271. Min Range: -2.7271

Max Act: 2.6259. Min Act: -0.1700

Data Index: 956813 (Open Web Text)

Max Activating Token Index: 667

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.7271. Min Range: -2.7271

Max Act: 2.6174. Min Act: -0.1700

Data Index: 1434490 (Open Web Text)

Max Activating Token Index: 307

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.7271. Min Range: -2.7271

Max Act: 2.5950. Min Act: -0.1700

Data Index: 4683975 (Open Web Text)

Max Activating Token Index: 455

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.7271. Min Range: -2.7271

Max Act: 2.6010. Min Act: -0.1700

Data Index: 3386733 (Open Web Text)

Max Activating Token Index: 988

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.7271. Min Range: -2.7271

Max Act: 2.5887. Min Act: -0.1700

Data Index: 7879098 (Open Web Text)

Max Activating Token Index: 730

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.7271. Min Range: -2.7271

Max Act: 2.5856. Min Act: -0.1700

Data Index: 8643929 (Open Web Text)

Max Activating Token Index: 377

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.7271. Min Range: -2.7271

Max Act: 2.6092. Min Act: -0.1700

Data Index: 6428900 (Open Web Text)

Max Activating Token Index: 799

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.7271. Min Range: -2.7271

Max Act: 2.5921. Min Act: -0.1700

Data Index: 2257806 (Open Web Text)

Max Activating Token Index: 845

Click toggle to see full text

Truncated

Full Text #19