< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 1613 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: 2.8039. Min Range: -2.8039

Max Act: 2.8039. Min Act: -0.1700

Data Index: 6626448 (Open Web Text)

Max Activating Token Index: 646

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.8039. Min Range: -2.8039

Max Act: 2.6823. Min Act: -0.1700

Data Index: 262210 (Open Web Text)

Max Activating Token Index: 583

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.8039. Min Range: -2.8039

Max Act: 2.6648. Min Act: -0.1700

Data Index: 6312450 (Open Web Text)

Max Activating Token Index: 798

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.8039. Min Range: -2.8039

Max Act: 2.6289. Min Act: -0.1700

Data Index: 5793519 (Open Web Text)

Max Activating Token Index: 947

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.8039. Min Range: -2.8039

Max Act: 2.6098. Min Act: -0.1700

Data Index: 1914291 (Open Web Text)

Max Activating Token Index: 231

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.8039. Min Range: -2.8039

Max Act: 2.6017. Min Act: -0.1700

Data Index: 5527597 (Open Web Text)

Max Activating Token Index: 131

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.8039. Min Range: -2.8039

Max Act: 2.5897. Min Act: -0.1700

Data Index: 8735692 (Open Web Text)

Max Activating Token Index: 812

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.8039. Min Range: -2.8039

Max Act: 2.5995. Min Act: -0.1700

Data Index: 6794422 (Open Web Text)

Max Activating Token Index: 344

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.8039. Min Range: -2.8039

Max Act: 2.5900. Min Act: -0.1700

Data Index: 8408045 (Open Web Text)

Max Activating Token Index: 745

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.8039. Min Range: -2.8039

Max Act: 2.5846. Min Act: -0.1700

Data Index: 1473126 (Open Web Text)

Max Activating Token Index: 570

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.8039. Min Range: -2.8039

Max Act: 2.5749. Min Act: -0.1700

Data Index: 3916349 (Open Web Text)

Max Activating Token Index: 763

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.8039. Min Range: -2.8039

Max Act: 2.5715. Min Act: -0.1700

Data Index: 7282645 (Open Web Text)

Max Activating Token Index: 729

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.8039. Min Range: -2.8039

Max Act: 2.5711. Min Act: -0.1700

Data Index: 123849 (Open Web Text)

Max Activating Token Index: 453

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.8039. Min Range: -2.8039

Max Act: 2.5910. Min Act: -0.1700

Data Index: 6791820 (Open Web Text)

Max Activating Token Index: 1016

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.8039. Min Range: -2.8039

Max Act: 2.5673. Min Act: -0.1700

Data Index: 6171286 (Open Web Text)

Max Activating Token Index: 67

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.8039. Min Range: -2.8039

Max Act: 2.5672. Min Act: -0.1700

Data Index: 4256015 (Open Web Text)

Max Activating Token Index: 180

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.8039. Min Range: -2.8039

Max Act: 2.5739. Min Act: -0.1700

Data Index: 703583 (Open Web Text)

Max Activating Token Index: 873

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.8039. Min Range: -2.8039

Max Act: 2.5722. Min Act: -0.1700

Data Index: 8086457 (Open Web Text)

Max Activating Token Index: 869

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.8039. Min Range: -2.8039

Max Act: 2.5681. Min Act: -0.1700

Data Index: 7840295 (Open Web Text)

Max Activating Token Index: 526

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.8039. Min Range: -2.8039

Max Act: 2.5720. Min Act: -0.1700

Data Index: 1968545 (Open Web Text)

Max Activating Token Index: 554

Click toggle to see full text

Truncated

Full Text #19