< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 430 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: 2.2818. Min Range: -2.2818

Max Act: 2.2818. Min Act: -0.1700

Data Index: 4064918 (Open Web Text)

Max Activating Token Index: 879

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.2818. Min Range: -2.2818

Max Act: 2.2130. Min Act: -0.1700

Data Index: 4269208 (Open Web Text)

Max Activating Token Index: 403

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.2818. Min Range: -2.2818

Max Act: 2.1816. Min Act: -0.1700

Data Index: 513310 (Open Web Text)

Max Activating Token Index: 913

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.2818. Min Range: -2.2818

Max Act: 2.1612. Min Act: -0.1700

Data Index: 8390802 (Open Web Text)

Max Activating Token Index: 903

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.2818. Min Range: -2.2818

Max Act: 2.1709. Min Act: -0.1700

Data Index: 1584393 (Open Web Text)

Max Activating Token Index: 162

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.2818. Min Range: -2.2818

Max Act: 2.1499. Min Act: -0.1700

Data Index: 7899833 (Open Web Text)

Max Activating Token Index: 582

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.2818. Min Range: -2.2818

Max Act: 2.1350. Min Act: -0.1700

Data Index: 8029447 (Open Web Text)

Max Activating Token Index: 115

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.2818. Min Range: -2.2818

Max Act: 2.1215. Min Act: -0.1700

Data Index: 4414798 (Open Web Text)

Max Activating Token Index: 10

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.2818. Min Range: -2.2818

Max Act: 2.1048. Min Act: -0.1700

Data Index: 8657955 (Open Web Text)

Max Activating Token Index: 962

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.2818. Min Range: -2.2818

Max Act: 2.1259. Min Act: -0.1700

Data Index: 621064 (Open Web Text)

Max Activating Token Index: 671

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.2818. Min Range: -2.2818

Max Act: 2.1606. Min Act: -0.1700

Data Index: 716489 (Open Web Text)

Max Activating Token Index: 911

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.2818. Min Range: -2.2818

Max Act: 2.1295. Min Act: -0.1700

Data Index: 4788329 (Open Web Text)

Max Activating Token Index: 239

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.2818. Min Range: -2.2818

Max Act: 2.0976. Min Act: -0.1700

Data Index: 6371930 (Open Web Text)

Max Activating Token Index: 581

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.2818. Min Range: -2.2818

Max Act: 2.1012. Min Act: -0.1700

Data Index: 6733306 (Open Web Text)

Max Activating Token Index: 940

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.2818. Min Range: -2.2818

Max Act: 2.0996. Min Act: -0.1700

Data Index: 1335251 (Open Web Text)

Max Activating Token Index: 913

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.2818. Min Range: -2.2818

Max Act: 2.1000. Min Act: -0.1700

Data Index: 5434915 (Open Web Text)

Max Activating Token Index: 392

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.2818. Min Range: -2.2818

Max Act: 2.1285. Min Act: -0.1700

Data Index: 2795705 (Open Web Text)

Max Activating Token Index: 503

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.2818. Min Range: -2.2818

Max Act: 2.1087. Min Act: -0.1700

Data Index: 3153789 (Open Web Text)

Max Activating Token Index: 138

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.2818. Min Range: -2.2818

Max Act: 2.1065. Min Act: -0.1700

Data Index: 2016890 (Open Web Text)

Max Activating Token Index: 420

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.2818. Min Range: -2.2818

Max Act: 2.0998. Min Act: -0.1700

Data Index: 1686498 (Open Web Text)

Max Activating Token Index: 555

Click toggle to see full text

Truncated

Full Text #19