< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 811 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: 2.8321. Min Range: -2.8321

Max Act: 2.8321. Min Act: -0.1700

Data Index: 2280751 (Open Web Text)

Max Activating Token Index: 999

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.8321. Min Range: -2.8321

Max Act: 2.7343. Min Act: -0.1700

Data Index: 7135927 (Open Web Text)

Max Activating Token Index: 78

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.8321. Min Range: -2.8321

Max Act: 2.7374. Min Act: -0.1700

Data Index: 7567626 (Open Web Text)

Max Activating Token Index: 811

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.8321. Min Range: -2.8321

Max Act: 2.6973. Min Act: -0.1700

Data Index: 1710272 (Open Web Text)

Max Activating Token Index: 948

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.8321. Min Range: -2.8321

Max Act: 2.6933. Min Act: -0.1700

Data Index: 2280750 (Open Web Text)

Max Activating Token Index: 61

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.8321. Min Range: -2.8321

Max Act: 2.7159. Min Act: -0.1700

Data Index: 6108572 (Open Web Text)

Max Activating Token Index: 255

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.8321. Min Range: -2.8321

Max Act: 2.6914. Min Act: -0.1700

Data Index: 4098389 (Open Web Text)

Max Activating Token Index: 12

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.8321. Min Range: -2.8321

Max Act: 2.6645. Min Act: -0.1700

Data Index: 1739921 (Open Web Text)

Max Activating Token Index: 21

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.8321. Min Range: -2.8321

Max Act: 2.6815. Min Act: -0.1700

Data Index: 5884956 (Open Web Text)

Max Activating Token Index: 385

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.8321. Min Range: -2.8321

Max Act: 2.6679. Min Act: -0.1700

Data Index: 3332652 (Open Web Text)

Max Activating Token Index: 338

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.8321. Min Range: -2.8321

Max Act: 2.6517. Min Act: -0.1700

Data Index: 7049425 (Open Web Text)

Max Activating Token Index: 28

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.8321. Min Range: -2.8321

Max Act: 2.6349. Min Act: -0.1700

Data Index: 1598855 (Open Web Text)

Max Activating Token Index: 627

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.8321. Min Range: -2.8321

Max Act: 2.6383. Min Act: -0.1700

Data Index: 2621736 (Open Web Text)

Max Activating Token Index: 514

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.8321. Min Range: -2.8321

Max Act: 2.6362. Min Act: -0.1700

Data Index: 7401791 (Open Web Text)

Max Activating Token Index: 636

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.8321. Min Range: -2.8321

Max Act: 2.6271. Min Act: -0.1700

Data Index: 5679066 (Open Web Text)

Max Activating Token Index: 523

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.8321. Min Range: -2.8321

Max Act: 2.6513. Min Act: -0.1700

Data Index: 7359670 (Open Web Text)

Max Activating Token Index: 988

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.8321. Min Range: -2.8321

Max Act: 2.6417. Min Act: -0.1700

Data Index: 331610 (Open Web Text)

Max Activating Token Index: 179

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.8321. Min Range: -2.8321

Max Act: 2.6380. Min Act: -0.1700

Data Index: 6111744 (Open Web Text)

Max Activating Token Index: 92

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.8321. Min Range: -2.8321

Max Act: 2.6354. Min Act: -0.1700

Data Index: 5763510 (Open Web Text)

Max Activating Token Index: 288

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.8321. Min Range: -2.8321

Max Act: 2.6149. Min Act: -0.1700

Data Index: 2670343 (Open Web Text)

Max Activating Token Index: 694

Click toggle to see full text

Truncated

Full Text #19