< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 2303 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')

Text #0

Max Range: 6.0667. Min Range: -6.0667

Max Act: 6.0667. Min Act: -0.1700

Data Index: 430164 (Open Web Text)

Max Activating Token Index: 617

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 6.0667. Min Range: -6.0667

Max Act: 6.0574. Min Act: -0.1700

Data Index: 4845895 (Open Web Text)

Max Activating Token Index: 180

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 6.0667. Min Range: -6.0667

Max Act: 6.0444. Min Act: -0.1700

Data Index: 4868938 (Open Web Text)

Max Activating Token Index: 662

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 6.0667. Min Range: -6.0667

Max Act: 5.9982. Min Act: -0.1700

Data Index: 4314530 (Open Web Text)

Max Activating Token Index: 231

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 6.0667. Min Range: -6.0667

Max Act: 5.9788. Min Act: -0.1700

Data Index: 7415092 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 6.0667. Min Range: -6.0667

Max Act: 5.9788. Min Act: -0.1700

Data Index: 5807122 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 6.0667. Min Range: -6.0667

Max Act: 5.9788. Min Act: -0.1700

Data Index: 2632421 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 6.0667. Min Range: -6.0667

Max Act: 5.9788. Min Act: -0.1700

Data Index: 5194017 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 6.0667. Min Range: -6.0667

Max Act: 5.9788. Min Act: -0.1700

Data Index: 5194003 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 6.0667. Min Range: -6.0667

Max Act: 5.9788. Min Act: -0.1700

Data Index: 2632398 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 6.0667. Min Range: -6.0667

Max Act: 6.0003. Min Act: -0.1700

Data Index: 2353214 (Open Web Text)

Max Activating Token Index: 317

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 6.0667. Min Range: -6.0667

Max Act: 5.9788. Min Act: -0.1700

Data Index: 4509163 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 6.0667. Min Range: -6.0667

Max Act: 5.9788. Min Act: -0.1700

Data Index: 5194031 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 6.0667. Min Range: -6.0667

Max Act: 5.9788. Min Act: -0.1700

Data Index: 5439136 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 6.0667. Min Range: -6.0667

Max Act: 5.9788. Min Act: -0.1700

Data Index: 6649791 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 6.0667. Min Range: -6.0667

Max Act: 5.9756. Min Act: -0.1700

Data Index: 6452209 (Open Web Text)

Max Activating Token Index: 907

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 6.0667. Min Range: -6.0667

Max Act: 5.9788. Min Act: -0.1700

Data Index: 6275251 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 6.0667. Min Range: -6.0667

Max Act: 5.9788. Min Act: -0.1700

Data Index: 5195478 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 6.0667. Min Range: -6.0667

Max Act: 5.9788. Min Act: -0.1700

Data Index: 5194028 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 6.0667. Min Range: -6.0667

Max Act: 5.9345. Min Act: -0.1700

Data Index: 130240 (Open Web Text)

Max Activating Token Index: 398

Click toggle to see full text

Truncated

Full Text #19