< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 1718 in Layer 6

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: 2.8229. Min Range: -2.8229

Max Act: 2.8229. Min Act: -0.1700

Data Index: 7335561 (Open Web Text)

Max Activating Token Index: 369

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.8229. Min Range: -2.8229

Max Act: 2.8093. Min Act: -0.1699

Data Index: 1272848 (Open Web Text)

Max Activating Token Index: 739

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.8229. Min Range: -2.8229

Max Act: 2.7773. Min Act: -0.1700

Data Index: 6325643 (Open Web Text)

Max Activating Token Index: 644

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.8229. Min Range: -2.8229

Max Act: 2.7842. Min Act: -0.1700

Data Index: 5823585 (Open Web Text)

Max Activating Token Index: 885

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.8229. Min Range: -2.8229

Max Act: 2.7474. Min Act: -0.1700

Data Index: 956150 (Open Web Text)

Max Activating Token Index: 836

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.8229. Min Range: -2.8229

Max Act: 2.7632. Min Act: -0.1700

Data Index: 4381620 (Open Web Text)

Max Activating Token Index: 799

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.8229. Min Range: -2.8229

Max Act: 2.7473. Min Act: -0.1700

Data Index: 4704124 (Open Web Text)

Max Activating Token Index: 909

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.8229. Min Range: -2.8229

Max Act: 2.7462. Min Act: -0.1700

Data Index: 6918139 (Open Web Text)

Max Activating Token Index: 181

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.8229. Min Range: -2.8229

Max Act: 2.7470. Min Act: -0.1700

Data Index: 6391580 (Open Web Text)

Max Activating Token Index: 552

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.8229. Min Range: -2.8229

Max Act: 2.7542. Min Act: -0.1700

Data Index: 6364775 (Open Web Text)

Max Activating Token Index: 963

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.8229. Min Range: -2.8229

Max Act: 2.7459. Min Act: -0.1700

Data Index: 3420722 (Open Web Text)

Max Activating Token Index: 501

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.8229. Min Range: -2.8229

Max Act: 2.7246. Min Act: -0.1700

Data Index: 3190686 (Open Web Text)

Max Activating Token Index: 390

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.8229. Min Range: -2.8229

Max Act: 2.7346. Min Act: -0.1700

Data Index: 3927459 (Open Web Text)

Max Activating Token Index: 641

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.8229. Min Range: -2.8229

Max Act: 2.7490. Min Act: -0.1700

Data Index: 5375247 (Open Web Text)

Max Activating Token Index: 929

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.8229. Min Range: -2.8229

Max Act: 2.7270. Min Act: -0.1700

Data Index: 5174315 (Open Web Text)

Max Activating Token Index: 801

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.8229. Min Range: -2.8229

Max Act: 2.7435. Min Act: -0.1700

Data Index: 5163103 (Open Web Text)

Max Activating Token Index: 839

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.8229. Min Range: -2.8229

Max Act: 2.7184. Min Act: -0.1700

Data Index: 7091227 (Open Web Text)

Max Activating Token Index: 467

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.8229. Min Range: -2.8229

Max Act: 2.7264. Min Act: -0.1700

Data Index: 4790330 (Open Web Text)

Max Activating Token Index: 269

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.8229. Min Range: -2.8229

Max Act: 2.7242. Min Act: -0.1700

Data Index: 5699869 (Open Web Text)

Max Activating Token Index: 746

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.8229. Min Range: -2.8229

Max Act: 2.7184. Min Act: -0.1700

Data Index: 4860462 (Open Web Text)

Max Activating Token Index: 415

Click toggle to see full text

Truncated

Full Text #19