< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 532 in Layer 0

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: 2.7274. Min Range: -2.7274

Max Act: 2.7274. Min Act: -0.1700

Data Index: 6858987 (Open Web Text)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.7274. Min Range: -2.7274

Max Act: 2.7138. Min Act: -0.1700

Data Index: 3710252 (Open Web Text)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.7274. Min Range: -2.7274

Max Act: 2.6704. Min Act: -0.1700

Data Index: 8153387 (Open Web Text)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.7274. Min Range: -2.7274

Max Act: 2.6619. Min Act: -0.1700

Data Index: 5304039 (Open Web Text)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.7274. Min Range: -2.7274

Max Act: 2.6513. Min Act: -0.1700

Data Index: 8274778 (Open Web Text)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.7274. Min Range: -2.7274

Max Act: 2.6594. Min Act: -0.1700

Data Index: 3975300 (Open Web Text)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.7274. Min Range: -2.7274

Max Act: 2.6324. Min Act: -0.1700

Data Index: 652760 (Open Web Text)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.7274. Min Range: -2.7274

Max Act: 2.6492. Min Act: -0.1700

Data Index: 5597224 (Open Web Text)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.7274. Min Range: -2.7274

Max Act: 2.6276. Min Act: -0.1700

Data Index: 3017810 (Open Web Text)

Max Activating Token Index: 698

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.7274. Min Range: -2.7274

Max Act: 2.6201. Min Act: -0.1700

Data Index: 1149063 (Open Web Text)

Max Activating Token Index: 13

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.7274. Min Range: -2.7274

Max Act: 2.6316. Min Act: -0.1700

Data Index: 8669289 (Open Web Text)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.7274. Min Range: -2.7274

Max Act: 2.6219. Min Act: -0.1700

Data Index: 4250817 (Open Web Text)

Max Activating Token Index: 21

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.7274. Min Range: -2.7274

Max Act: 2.6326. Min Act: -0.1700

Data Index: 3443336 (Open Web Text)

Max Activating Token Index: 13

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.7274. Min Range: -2.7274

Max Act: 2.6272. Min Act: -0.1700

Data Index: 2411835 (Open Web Text)

Max Activating Token Index: 838

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.7274. Min Range: -2.7274

Max Act: 2.6073. Min Act: -0.1700

Data Index: 7444597 (Open Web Text)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.7274. Min Range: -2.7274

Max Act: 2.6072. Min Act: -0.1700

Data Index: 6384893 (Open Web Text)

Max Activating Token Index: 8

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.7274. Min Range: -2.7274

Max Act: 2.5980. Min Act: -0.1700

Data Index: 5948879 (Open Web Text)

Max Activating Token Index: 11

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.7274. Min Range: -2.7274

Max Act: 2.6011. Min Act: -0.1700

Data Index: 1079563 (Open Web Text)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.7274. Min Range: -2.7274

Max Act: 2.5918. Min Act: -0.1700

Data Index: 5731764 (Open Web Text)

Max Activating Token Index: 55

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.7274. Min Range: -2.7274

Max Act: 2.5949. Min Act: -0.1700

Data Index: 4157857 (Open Web Text)

Max Activating Token Index: 26

Click toggle to see full text

Truncated

Full Text #19