< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 2486 in Layer 2

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: 2.6930. Min Range: -2.6930

Max Act: 2.6930. Min Act: -0.1700

Data Index: 8250998 (Open Web Text)

Max Activating Token Index: 82

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.6930. Min Range: -2.6930

Max Act: 2.6736. Min Act: -0.1700

Data Index: 6635322 (Open Web Text)

Max Activating Token Index: 31

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.6930. Min Range: -2.6930

Max Act: 2.6618. Min Act: -0.1700

Data Index: 1908236 (Open Web Text)

Max Activating Token Index: 671

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.6930. Min Range: -2.6930

Max Act: 2.6371. Min Act: -0.1700

Data Index: 5038576 (Open Web Text)

Max Activating Token Index: 534

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.6930. Min Range: -2.6930

Max Act: 2.6094. Min Act: -0.1700

Data Index: 7034088 (Open Web Text)

Max Activating Token Index: 774

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.6930. Min Range: -2.6930

Max Act: 2.6286. Min Act: -0.1700

Data Index: 2548073 (Open Web Text)

Max Activating Token Index: 136

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.6930. Min Range: -2.6930

Max Act: 2.6150. Min Act: -0.1700

Data Index: 5632448 (Open Web Text)

Max Activating Token Index: 94

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.6930. Min Range: -2.6930

Max Act: 2.6145. Min Act: -0.1700

Data Index: 8388342 (Open Web Text)

Max Activating Token Index: 835

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.6930. Min Range: -2.6930

Max Act: 2.5881. Min Act: -0.1700

Data Index: 8698337 (Open Web Text)

Max Activating Token Index: 328

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.6930. Min Range: -2.6930

Max Act: 2.5858. Min Act: -0.1700

Data Index: 2190094 (Open Web Text)

Max Activating Token Index: 465

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.6930. Min Range: -2.6930

Max Act: 2.5869. Min Act: -0.1700

Data Index: 7049227 (Open Web Text)

Max Activating Token Index: 880

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.6930. Min Range: -2.6930

Max Act: 2.5667. Min Act: -0.1700

Data Index: 5441420 (Open Web Text)

Max Activating Token Index: 955

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.6930. Min Range: -2.6930

Max Act: 2.5667. Min Act: -0.1700

Data Index: 7004968 (Open Web Text)

Max Activating Token Index: 899

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.6930. Min Range: -2.6930

Max Act: 2.5506. Min Act: -0.1700

Data Index: 3651444 (Open Web Text)

Max Activating Token Index: 910

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.6930. Min Range: -2.6930

Max Act: 2.5278. Min Act: -0.1700

Data Index: 5482185 (Open Web Text)

Max Activating Token Index: 764

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.6930. Min Range: -2.6930

Max Act: 2.5408. Min Act: -0.1700

Data Index: 2809691 (Open Web Text)

Max Activating Token Index: 999

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.6930. Min Range: -2.6930

Max Act: 2.5544. Min Act: -0.1700

Data Index: 7840569 (Open Web Text)

Max Activating Token Index: 327

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.6930. Min Range: -2.6930

Max Act: 2.5331. Min Act: -0.1700

Data Index: 2976301 (Open Web Text)

Max Activating Token Index: 687

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.6930. Min Range: -2.6930

Max Act: 2.5393. Min Act: -0.1700

Data Index: 4424698 (Open Web Text)

Max Activating Token Index: 212

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.6930. Min Range: -2.6930

Max Act: 2.5354. Min Act: -0.1700

Data Index: 4924758 (Open Web Text)

Max Activating Token Index: 125

Click toggle to see full text

Truncated

Full Text #19