< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 56 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: 4.2936. Min Range: -4.2936

Max Act: 4.2936. Min Act: -0.1700

Data Index: 8549087 (Open Web Text)

Max Activating Token Index: 891

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 4.2936. Min Range: -4.2936

Max Act: 4.2895. Min Act: -0.1700

Data Index: 43511 (Open Web Text)

Max Activating Token Index: 810

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 4.2936. Min Range: -4.2936

Max Act: 4.2193. Min Act: -0.1700

Data Index: 855849 (Open Web Text)

Max Activating Token Index: 426

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 4.2936. Min Range: -4.2936

Max Act: 4.2394. Min Act: -0.1700

Data Index: 7321435 (Open Web Text)

Max Activating Token Index: 267

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 4.2936. Min Range: -4.2936

Max Act: 4.2004. Min Act: -0.1700

Data Index: 206875 (Open Web Text)

Max Activating Token Index: 638

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 4.2936. Min Range: -4.2936

Max Act: 4.2311. Min Act: -0.1700

Data Index: 1470483 (Open Web Text)

Max Activating Token Index: 579

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 4.2936. Min Range: -4.2936

Max Act: 4.1506. Min Act: -0.1700

Data Index: 4248586 (Open Web Text)

Max Activating Token Index: 823

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 4.2936. Min Range: -4.2936

Max Act: 4.1762. Min Act: -0.1700

Data Index: 4888409 (Open Web Text)

Max Activating Token Index: 20

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 4.2936. Min Range: -4.2936

Max Act: 4.1497. Min Act: -0.1700

Data Index: 5393874 (Open Web Text)

Max Activating Token Index: 130

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 4.2936. Min Range: -4.2936

Max Act: 4.1830. Min Act: -0.1700

Data Index: 274988 (Open Web Text)

Max Activating Token Index: 115

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 4.2936. Min Range: -4.2936

Max Act: 4.1576. Min Act: -0.1700

Data Index: 7494890 (Open Web Text)

Max Activating Token Index: 499

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 4.2936. Min Range: -4.2936

Max Act: 4.1199. Min Act: -0.1700

Data Index: 2704055 (Open Web Text)

Max Activating Token Index: 320

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 4.2936. Min Range: -4.2936

Max Act: 4.1168. Min Act: -0.1700

Data Index: 4272790 (Open Web Text)

Max Activating Token Index: 880

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 4.2936. Min Range: -4.2936

Max Act: 4.1279. Min Act: -0.1700

Data Index: 4145738 (Open Web Text)

Max Activating Token Index: 293

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 4.2936. Min Range: -4.2936

Max Act: 4.1180. Min Act: -0.1700

Data Index: 477358 (Open Web Text)

Max Activating Token Index: 26

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 4.2936. Min Range: -4.2936

Max Act: 4.1038. Min Act: -0.1700

Data Index: 2387826 (Open Web Text)

Max Activating Token Index: 494

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 4.2936. Min Range: -4.2936

Max Act: 4.1054. Min Act: -0.1700

Data Index: 3100704 (Open Web Text)

Max Activating Token Index: 871

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 4.2936. Min Range: -4.2936

Max Act: 4.0854. Min Act: -0.1700

Data Index: 4735348 (Open Web Text)

Max Activating Token Index: 684

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 4.2936. Min Range: -4.2936

Max Act: 4.0750. Min Act: -0.1700

Data Index: 453338 (Open Web Text)

Max Activating Token Index: 154

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 4.2936. Min Range: -4.2936

Max Act: 4.0872. Min Act: -0.1700

Data Index: 3265607 (Open Web Text)

Max Activating Token Index: 829

Click toggle to see full text

Truncated

Full Text #19