< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 571 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: 2.2262. Min Range: -2.2262

Max Act: 2.2200. Min Act: -0.1700

Data Index: 4694080 (Open Web Text)

Max Activating Token Index: 969

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.2262. Min Range: -2.2262

Max Act: 2.2010. Min Act: -0.1700

Data Index: 5001134 (Open Web Text)

Max Activating Token Index: 42

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.2262. Min Range: -2.2262

Max Act: 2.2262. Min Act: -0.1700

Data Index: 4505688 (Open Web Text)

Max Activating Token Index: 322

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.2262. Min Range: -2.2262

Max Act: 2.2015. Min Act: -0.1700

Data Index: 7908377 (Open Web Text)

Max Activating Token Index: 89

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.2262. Min Range: -2.2262

Max Act: 2.1701. Min Act: -0.1700

Data Index: 5748864 (Open Web Text)

Max Activating Token Index: 818

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.2262. Min Range: -2.2262

Max Act: 2.1778. Min Act: -0.1700

Data Index: 3992750 (Open Web Text)

Max Activating Token Index: 41

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.2262. Min Range: -2.2262

Max Act: 2.1624. Min Act: -0.1700

Data Index: 2983192 (Open Web Text)

Max Activating Token Index: 152

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.2262. Min Range: -2.2262

Max Act: 2.1463. Min Act: -0.1700

Data Index: 4958186 (Open Web Text)

Max Activating Token Index: 897

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.2262. Min Range: -2.2262

Max Act: 2.1471. Min Act: -0.1700

Data Index: 5567803 (Open Web Text)

Max Activating Token Index: 602

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.2262. Min Range: -2.2262

Max Act: 2.1640. Min Act: -0.1700

Data Index: 6920305 (Open Web Text)

Max Activating Token Index: 229

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.2262. Min Range: -2.2262

Max Act: 2.1598. Min Act: -0.1700

Data Index: 4258961 (Open Web Text)

Max Activating Token Index: 773

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.2262. Min Range: -2.2262

Max Act: 2.1289. Min Act: -0.1700

Data Index: 4465139 (Open Web Text)

Max Activating Token Index: 564

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.2262. Min Range: -2.2262

Max Act: 2.1497. Min Act: -0.1700

Data Index: 789719 (Open Web Text)

Max Activating Token Index: 64

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.2262. Min Range: -2.2262

Max Act: 2.1311. Min Act: -0.1700

Data Index: 6013131 (Open Web Text)

Max Activating Token Index: 195

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.2262. Min Range: -2.2262

Max Act: 2.1430. Min Act: -0.1700

Data Index: 4916091 (Open Web Text)

Max Activating Token Index: 85

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.2262. Min Range: -2.2262

Max Act: 2.1520. Min Act: -0.1700

Data Index: 1096722 (Open Web Text)

Max Activating Token Index: 230

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.2262. Min Range: -2.2262

Max Act: 2.1263. Min Act: -0.1700

Data Index: 7908370 (Open Web Text)

Max Activating Token Index: 889

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.2262. Min Range: -2.2262

Max Act: 2.1361. Min Act: -0.1700

Data Index: 1039224 (Open Web Text)

Max Activating Token Index: 1021

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.2262. Min Range: -2.2262

Max Act: 2.1383. Min Act: -0.1700

Data Index: 6760644 (Open Web Text)

Max Activating Token Index: 794

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.2262. Min Range: -2.2262

Max Act: 2.1264. Min Act: -0.1700

Data Index: 6914641 (Open Web Text)

Max Activating Token Index: 66

Click toggle to see full text

Truncated

Full Text #19