< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 405 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')

Text #0

Max Range: 2.6850. Min Range: -2.6850

Max Act: 2.6850. Min Act: -0.1700

Data Index: 666226 (Open Web Text)

Max Activating Token Index: 999

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.6850. Min Range: -2.6850

Max Act: 2.6825. Min Act: -0.1700

Data Index: 7934531 (Open Web Text)

Max Activating Token Index: 270

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.6850. Min Range: -2.6850

Max Act: 2.6402. Min Act: -0.1700

Data Index: 4608440 (Open Web Text)

Max Activating Token Index: 364

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.6850. Min Range: -2.6850

Max Act: 2.6638. Min Act: -0.1700

Data Index: 830301 (Open Web Text)

Max Activating Token Index: 795

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.6850. Min Range: -2.6850

Max Act: 2.6216. Min Act: -0.1700

Data Index: 5402963 (Open Web Text)

Max Activating Token Index: 130

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.6850. Min Range: -2.6850

Max Act: 2.6569. Min Act: -0.1700

Data Index: 1419599 (Open Web Text)

Max Activating Token Index: 538

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.6850. Min Range: -2.6850

Max Act: 2.6146. Min Act: -0.1700

Data Index: 4888701 (Open Web Text)

Max Activating Token Index: 538

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.6850. Min Range: -2.6850

Max Act: 2.6234. Min Act: -0.1700

Data Index: 4788151 (Open Web Text)

Max Activating Token Index: 915

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.6850. Min Range: -2.6850

Max Act: 2.6320. Min Act: -0.1700

Data Index: 3647451 (Open Web Text)

Max Activating Token Index: 984

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.6850. Min Range: -2.6850

Max Act: 2.6087. Min Act: -0.1700

Data Index: 1699546 (Open Web Text)

Max Activating Token Index: 924

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.6850. Min Range: -2.6850

Max Act: 2.6117. Min Act: -0.1700

Data Index: 370434 (Open Web Text)

Max Activating Token Index: 286

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.6850. Min Range: -2.6850

Max Act: 2.5998. Min Act: -0.1700

Data Index: 1770600 (Open Web Text)

Max Activating Token Index: 842

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.6850. Min Range: -2.6850

Max Act: 2.6180. Min Act: -0.1700

Data Index: 4428300 (Open Web Text)

Max Activating Token Index: 138

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.6850. Min Range: -2.6850

Max Act: 2.6049. Min Act: -0.1700

Data Index: 3136859 (Open Web Text)

Max Activating Token Index: 917

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.6850. Min Range: -2.6850

Max Act: 2.5875. Min Act: -0.1700

Data Index: 3782487 (Open Web Text)

Max Activating Token Index: 170

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.6850. Min Range: -2.6850

Max Act: 2.5926. Min Act: -0.1700

Data Index: 333319 (Open Web Text)

Max Activating Token Index: 490

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.6850. Min Range: -2.6850

Max Act: 2.5970. Min Act: -0.1700

Data Index: 5697939 (Open Web Text)

Max Activating Token Index: 933

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.6850. Min Range: -2.6850

Max Act: 2.6213. Min Act: -0.1700

Data Index: 7731655 (Open Web Text)

Max Activating Token Index: 606

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.6850. Min Range: -2.6850

Max Act: 2.5915. Min Act: -0.1700

Data Index: 4217976 (Open Web Text)

Max Activating Token Index: 428

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.6850. Min Range: -2.6850

Max Act: 2.5655. Min Act: -0.1700

Data Index: 6133439 (Open Web Text)

Max Activating Token Index: 184

Click toggle to see full text

Truncated

Full Text #19