< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 460 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: 2.4374. Min Range: -2.4374

Max Act: 2.4374. Min Act: -0.1700

Data Index: 1631675 (Open Web Text)

Max Activating Token Index: 528

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.4374. Min Range: -2.4374

Max Act: 2.3508. Min Act: -0.1700

Data Index: 156171 (Open Web Text)

Max Activating Token Index: 951

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.4374. Min Range: -2.4374

Max Act: 2.2901. Min Act: -0.1700

Data Index: 3678636 (Open Web Text)

Max Activating Token Index: 384

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.4374. Min Range: -2.4374

Max Act: 2.2751. Min Act: -0.1700

Data Index: 5719091 (Open Web Text)

Max Activating Token Index: 884

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.4374. Min Range: -2.4374

Max Act: 2.2477. Min Act: -0.1700

Data Index: 235172 (Open Web Text)

Max Activating Token Index: 147

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.4374. Min Range: -2.4374

Max Act: 2.2416. Min Act: -0.1700

Data Index: 2194871 (Open Web Text)

Max Activating Token Index: 179

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.4374. Min Range: -2.4374

Max Act: 2.2224. Min Act: -0.1700

Data Index: 5399733 (Open Web Text)

Max Activating Token Index: 407

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.4374. Min Range: -2.4374

Max Act: 2.2360. Min Act: -0.1700

Data Index: 2474878 (Open Web Text)

Max Activating Token Index: 933

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.4374. Min Range: -2.4374

Max Act: 2.2251. Min Act: -0.1700

Data Index: 5419107 (Open Web Text)

Max Activating Token Index: 893

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.4374. Min Range: -2.4374

Max Act: 2.2189. Min Act: -0.1700

Data Index: 8052088 (Open Web Text)

Max Activating Token Index: 575

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.4374. Min Range: -2.4374

Max Act: 2.2068. Min Act: -0.1700

Data Index: 7650059 (Open Web Text)

Max Activating Token Index: 417

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.4374. Min Range: -2.4374

Max Act: 2.2157. Min Act: -0.1700

Data Index: 610019 (Open Web Text)

Max Activating Token Index: 340

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.4374. Min Range: -2.4374

Max Act: 2.1861. Min Act: -0.1700

Data Index: 219859 (Open Web Text)

Max Activating Token Index: 563

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.4374. Min Range: -2.4374

Max Act: 2.2042. Min Act: -0.1700

Data Index: 1481765 (Open Web Text)

Max Activating Token Index: 919

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.4374. Min Range: -2.4374

Max Act: 2.1580. Min Act: -0.1700

Data Index: 7038230 (Open Web Text)

Max Activating Token Index: 559

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.4374. Min Range: -2.4374

Max Act: 2.2098. Min Act: -0.1700

Data Index: 7690438 (Open Web Text)

Max Activating Token Index: 752

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.4374. Min Range: -2.4374

Max Act: 2.1720. Min Act: -0.1700

Data Index: 4521704 (Open Web Text)

Max Activating Token Index: 50

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.4374. Min Range: -2.4374

Max Act: 2.2090. Min Act: -0.1700

Data Index: 5419103 (Open Web Text)

Max Activating Token Index: 494

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.4374. Min Range: -2.4374

Max Act: 2.1824. Min Act: -0.1700

Data Index: 4065087 (Open Web Text)

Max Activating Token Index: 863

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.4374. Min Range: -2.4374

Max Act: 2.1749. Min Act: -0.1700

Data Index: 8290363 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #19