< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 41 in Layer 5

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: 2.7927. Min Range: -2.7927

Max Act: 2.7927. Min Act: -0.1700

Data Index: 8585403 (Open Web Text)

Max Activating Token Index: 813

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.7927. Min Range: -2.7927

Max Act: 2.7787. Min Act: -0.1700

Data Index: 3846188 (Open Web Text)

Max Activating Token Index: 757

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.7927. Min Range: -2.7927

Max Act: 2.7665. Min Act: -0.1700

Data Index: 3581372 (Open Web Text)

Max Activating Token Index: 260

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.7927. Min Range: -2.7927

Max Act: 2.7604. Min Act: -0.1700

Data Index: 4922088 (Open Web Text)

Max Activating Token Index: 880

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.7927. Min Range: -2.7927

Max Act: 2.7409. Min Act: -0.1700

Data Index: 4163281 (Open Web Text)

Max Activating Token Index: 617

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.7927. Min Range: -2.7927

Max Act: 2.7366. Min Act: -0.1700

Data Index: 1709149 (Open Web Text)

Max Activating Token Index: 224

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.7927. Min Range: -2.7927

Max Act: 2.7366. Min Act: -0.1700

Data Index: 7072600 (Open Web Text)

Max Activating Token Index: 736

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.7927. Min Range: -2.7927

Max Act: 2.7169. Min Act: -0.1700

Data Index: 5448738 (Open Web Text)

Max Activating Token Index: 134

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.7927. Min Range: -2.7927

Max Act: 2.7285. Min Act: -0.1700

Data Index: 4473056 (Open Web Text)

Max Activating Token Index: 542

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.7927. Min Range: -2.7927

Max Act: 2.7258. Min Act: -0.1700

Data Index: 3345349 (Open Web Text)

Max Activating Token Index: 485

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.7927. Min Range: -2.7927

Max Act: 2.6827. Min Act: -0.1700

Data Index: 4178552 (Open Web Text)

Max Activating Token Index: 1018

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.7927. Min Range: -2.7927

Max Act: 2.7122. Min Act: -0.1700

Data Index: 6575951 (Open Web Text)

Max Activating Token Index: 485

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.7927. Min Range: -2.7927

Max Act: 2.6986. Min Act: -0.1700

Data Index: 1856536 (Open Web Text)

Max Activating Token Index: 40

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.7927. Min Range: -2.7927

Max Act: 2.7057. Min Act: -0.1700

Data Index: 4178553 (Open Web Text)

Max Activating Token Index: 336

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.7927. Min Range: -2.7927

Max Act: 2.7141. Min Act: -0.1700

Data Index: 1929830 (Open Web Text)

Max Activating Token Index: 312

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.7927. Min Range: -2.7927

Max Act: 2.6869. Min Act: -0.1700

Data Index: 8552859 (Open Web Text)

Max Activating Token Index: 133

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.7927. Min Range: -2.7927

Max Act: 2.6768. Min Act: -0.1700

Data Index: 5043503 (Open Web Text)

Max Activating Token Index: 722

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.7927. Min Range: -2.7927

Max Act: 2.6893. Min Act: -0.1700

Data Index: 840801 (Open Web Text)

Max Activating Token Index: 459

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.7927. Min Range: -2.7927

Max Act: 2.6917. Min Act: -0.1700

Data Index: 2779453 (Open Web Text)

Max Activating Token Index: 832

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.7927. Min Range: -2.7927

Max Act: 2.6853. Min Act: -0.1700

Data Index: 3541243 (Open Web Text)

Max Activating Token Index: 900

Click toggle to see full text

Truncated

Full Text #19