< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 857 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: 2.8065. Min Range: -2.8065

Max Act: 2.8065. Min Act: -0.1700

Data Index: 6520015 (Open Web Text)

Max Activating Token Index: 31

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.8065. Min Range: -2.8065

Max Act: 2.7279. Min Act: -0.1700

Data Index: 2106995 (Open Web Text)

Max Activating Token Index: 403

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.8065. Min Range: -2.8065

Max Act: 2.7294. Min Act: -0.1700

Data Index: 6034697 (Open Web Text)

Max Activating Token Index: 790

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.8065. Min Range: -2.8065

Max Act: 2.6905. Min Act: -0.1700

Data Index: 776307 (Open Web Text)

Max Activating Token Index: 9

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.8065. Min Range: -2.8065

Max Act: 2.7260. Min Act: -0.1700

Data Index: 2641845 (Open Web Text)

Max Activating Token Index: 580

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.8065. Min Range: -2.8065

Max Act: 2.6782. Min Act: -0.1700

Data Index: 7945089 (Open Web Text)

Max Activating Token Index: 480

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.8065. Min Range: -2.8065

Max Act: 2.6750. Min Act: -0.1700

Data Index: 2949186 (Open Web Text)

Max Activating Token Index: 65

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.8065. Min Range: -2.8065

Max Act: 2.6756. Min Act: -0.1700

Data Index: 7300564 (Open Web Text)

Max Activating Token Index: 309

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.8065. Min Range: -2.8065

Max Act: 2.5965. Min Act: -0.1700

Data Index: 8815391 (Open Web Text)

Max Activating Token Index: 311

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.8065. Min Range: -2.8065

Max Act: 2.6168. Min Act: -0.1700

Data Index: 8559660 (Open Web Text)

Max Activating Token Index: 318

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.8065. Min Range: -2.8065

Max Act: 2.6315. Min Act: -0.1700

Data Index: 7519988 (Open Web Text)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.8065. Min Range: -2.8065

Max Act: 2.5876. Min Act: -0.1700

Data Index: 8592496 (Open Web Text)

Max Activating Token Index: 275

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.8065. Min Range: -2.8065

Max Act: 2.5954. Min Act: -0.1700

Data Index: 7646717 (Open Web Text)

Max Activating Token Index: 734

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.8065. Min Range: -2.8065

Max Act: 2.6006. Min Act: -0.1700

Data Index: 2561408 (Open Web Text)

Max Activating Token Index: 14

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.8065. Min Range: -2.8065

Max Act: 2.5972. Min Act: -0.1700

Data Index: 5229805 (Open Web Text)

Max Activating Token Index: 414

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.8065. Min Range: -2.8065

Max Act: 2.6040. Min Act: -0.1700

Data Index: 3355828 (Open Web Text)

Max Activating Token Index: 1021

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.8065. Min Range: -2.8065

Max Act: 2.5787. Min Act: -0.1700

Data Index: 3431153 (Open Web Text)

Max Activating Token Index: 41

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.8065. Min Range: -2.8065

Max Act: 2.5946. Min Act: -0.1700

Data Index: 7115027 (Open Web Text)

Max Activating Token Index: 341

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.8065. Min Range: -2.8065

Max Act: 2.5831. Min Act: -0.1700

Data Index: 4427601 (Open Web Text)

Max Activating Token Index: 561

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.8065. Min Range: -2.8065

Max Act: 2.5975. Min Act: -0.1700

Data Index: 5184863 (Open Web Text)

Max Activating Token Index: 321

Click toggle to see full text

Truncated

Full Text #19