< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 392 in Layer 6

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: 2.3861. Min Range: -2.3861

Max Act: 2.3861. Min Act: -0.1700

Data Index: 4811171 (Open Web Text)

Max Activating Token Index: 860

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.3861. Min Range: -2.3861

Max Act: 2.2938. Min Act: -0.1700

Data Index: 6005745 (Open Web Text)

Max Activating Token Index: 365

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.3861. Min Range: -2.3861

Max Act: 2.2815. Min Act: -0.1700

Data Index: 4384759 (Open Web Text)

Max Activating Token Index: 704

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.3861. Min Range: -2.3861

Max Act: 2.2890. Min Act: -0.1700

Data Index: 4811174 (Open Web Text)

Max Activating Token Index: 91

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.3861. Min Range: -2.3861

Max Act: 2.2062. Min Act: -0.1700

Data Index: 8047013 (Open Web Text)

Max Activating Token Index: 679

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.3861. Min Range: -2.3861

Max Act: 2.1430. Min Act: -0.1700

Data Index: 3137916 (Open Web Text)

Max Activating Token Index: 765

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.3861. Min Range: -2.3861

Max Act: 2.1414. Min Act: -0.1700

Data Index: 2906348 (Open Web Text)

Max Activating Token Index: 890

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.3861. Min Range: -2.3861

Max Act: 2.1047. Min Act: -0.1700

Data Index: 6888380 (Open Web Text)

Max Activating Token Index: 341

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.3861. Min Range: -2.3861

Max Act: 2.1260. Min Act: -0.1700

Data Index: 4662669 (Open Web Text)

Max Activating Token Index: 565

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.3861. Min Range: -2.3861

Max Act: 2.1153. Min Act: -0.1700

Data Index: 5374305 (Open Web Text)

Max Activating Token Index: 835

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.3861. Min Range: -2.3861

Max Act: 2.0816. Min Act: -0.1700

Data Index: 5681390 (Open Web Text)

Max Activating Token Index: 567

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.3861. Min Range: -2.3861

Max Act: 2.1298. Min Act: -0.1700

Data Index: 8246904 (Open Web Text)

Max Activating Token Index: 136

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.3861. Min Range: -2.3861

Max Act: 2.1370. Min Act: -0.1700

Data Index: 2357203 (Open Web Text)

Max Activating Token Index: 590

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.3861. Min Range: -2.3861

Max Act: 2.0814. Min Act: -0.1700

Data Index: 6417196 (Open Web Text)

Max Activating Token Index: 398

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.3861. Min Range: -2.3861

Max Act: 2.0433. Min Act: -0.1700

Data Index: 7967702 (Open Web Text)

Max Activating Token Index: 923

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.3861. Min Range: -2.3861

Max Act: 2.0819. Min Act: -0.1700

Data Index: 4350217 (Open Web Text)

Max Activating Token Index: 392

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.3861. Min Range: -2.3861

Max Act: 2.1012. Min Act: -0.1700

Data Index: 3738892 (Open Web Text)

Max Activating Token Index: 91

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.3861. Min Range: -2.3861

Max Act: 2.0850. Min Act: -0.1700

Data Index: 8358700 (Open Web Text)

Max Activating Token Index: 617

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.3861. Min Range: -2.3861

Max Act: 2.0700. Min Act: -0.1700

Data Index: 3907240 (Open Web Text)

Max Activating Token Index: 705

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.3861. Min Range: -2.3861

Max Act: 2.0841. Min Act: -0.1700

Data Index: 8147586 (Open Web Text)

Max Activating Token Index: 598

Click toggle to see full text

Truncated

Full Text #19