< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 2972 in Layer 3

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: 2.9989. Min Range: -2.9989

Max Act: 2.9989. Min Act: -0.1700

Data Index: 7372794 (Open Web Text)

Max Activating Token Index: 605

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.9989. Min Range: -2.9989

Max Act: 2.8800. Min Act: -0.1700

Data Index: 78768 (Open Web Text)

Max Activating Token Index: 687

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.9989. Min Range: -2.9989

Max Act: 2.8389. Min Act: -0.1700

Data Index: 8048986 (Open Web Text)

Max Activating Token Index: 8

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.9989. Min Range: -2.9989

Max Act: 2.8355. Min Act: -0.1700

Data Index: 8296627 (Open Web Text)

Max Activating Token Index: 649

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.9989. Min Range: -2.9989

Max Act: 2.8187. Min Act: -0.1700

Data Index: 4650227 (Open Web Text)

Max Activating Token Index: 862

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.9989. Min Range: -2.9989

Max Act: 2.8511. Min Act: -0.1700

Data Index: 171771 (Open Web Text)

Max Activating Token Index: 621

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.9989. Min Range: -2.9989

Max Act: 2.8515. Min Act: -0.1700

Data Index: 8465822 (Open Web Text)

Max Activating Token Index: 998

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.9989. Min Range: -2.9989

Max Act: 2.8204. Min Act: -0.1700

Data Index: 860782 (Open Web Text)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.9989. Min Range: -2.9989

Max Act: 2.8235. Min Act: -0.1700

Data Index: 2393082 (Open Web Text)

Max Activating Token Index: 760

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.9989. Min Range: -2.9989

Max Act: 2.8095. Min Act: -0.1700

Data Index: 382941 (Open Web Text)

Max Activating Token Index: 318

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.9989. Min Range: -2.9989

Max Act: 2.8156. Min Act: -0.1700

Data Index: 1262714 (Open Web Text)

Max Activating Token Index: 53

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.9989. Min Range: -2.9989

Max Act: 2.8103. Min Act: -0.1700

Data Index: 7881041 (Open Web Text)

Max Activating Token Index: 869

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.9989. Min Range: -2.9989

Max Act: 2.8029. Min Act: -0.1700

Data Index: 6956391 (Open Web Text)

Max Activating Token Index: 237

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.9989. Min Range: -2.9989

Max Act: 2.7936. Min Act: -0.1700

Data Index: 207615 (Open Web Text)

Max Activating Token Index: 515

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.9989. Min Range: -2.9989

Max Act: 2.7996. Min Act: -0.1700

Data Index: 4627826 (Open Web Text)

Max Activating Token Index: 38

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.9989. Min Range: -2.9989

Max Act: 2.7929. Min Act: -0.1700

Data Index: 2697784 (Open Web Text)

Max Activating Token Index: 80

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.9989. Min Range: -2.9989

Max Act: 2.7783. Min Act: -0.1700

Data Index: 2350860 (Open Web Text)

Max Activating Token Index: 583

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.9989. Min Range: -2.9989

Max Act: 2.7619. Min Act: -0.1700

Data Index: 7427437 (Open Web Text)

Max Activating Token Index: 618

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.9989. Min Range: -2.9989

Max Act: 2.7554. Min Act: -0.1700

Data Index: 2135063 (Open Web Text)

Max Activating Token Index: 554

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.9989. Min Range: -2.9989

Max Act: 2.7758. Min Act: -0.1700

Data Index: 7107730 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #19