< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 2744 in Layer 5

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: 2.7829. Min Range: -2.7829

Max Act: 2.7829. Min Act: -0.1700

Data Index: 4404468 (Open Web Text)

Max Activating Token Index: 479

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.7829. Min Range: -2.7829

Max Act: 2.7740. Min Act: -0.1700

Data Index: 5323023 (Open Web Text)

Max Activating Token Index: 942

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.7829. Min Range: -2.7829

Max Act: 2.7814. Min Act: -0.1700

Data Index: 457995 (Open Web Text)

Max Activating Token Index: 332

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.7829. Min Range: -2.7829

Max Act: 2.7721. Min Act: -0.1700

Data Index: 2058504 (Open Web Text)

Max Activating Token Index: 506

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.7829. Min Range: -2.7829

Max Act: 2.7659. Min Act: -0.1700

Data Index: 4577266 (Open Web Text)

Max Activating Token Index: 388

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.7829. Min Range: -2.7829

Max Act: 2.7381. Min Act: -0.1700

Data Index: 6434427 (Open Web Text)

Max Activating Token Index: 388

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.7829. Min Range: -2.7829

Max Act: 2.7485. Min Act: -0.1700

Data Index: 1613998 (Open Web Text)

Max Activating Token Index: 623

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.7829. Min Range: -2.7829

Max Act: 2.7198. Min Act: -0.1700

Data Index: 8739652 (Open Web Text)

Max Activating Token Index: 120

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.7829. Min Range: -2.7829

Max Act: 2.7386. Min Act: -0.1700

Data Index: 6500491 (Open Web Text)

Max Activating Token Index: 816

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.7829. Min Range: -2.7829

Max Act: 2.7302. Min Act: -0.1700

Data Index: 2092675 (Open Web Text)

Max Activating Token Index: 212

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.7829. Min Range: -2.7829

Max Act: 2.7090. Min Act: -0.1700

Data Index: 5615638 (Open Web Text)

Max Activating Token Index: 159

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.7829. Min Range: -2.7829

Max Act: 2.7024. Min Act: -0.1700

Data Index: 3868290 (Open Web Text)

Max Activating Token Index: 181

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.7829. Min Range: -2.7829

Max Act: 2.7064. Min Act: -0.1700

Data Index: 5990094 (Open Web Text)

Max Activating Token Index: 270

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.7829. Min Range: -2.7829

Max Act: 2.6890. Min Act: -0.1700

Data Index: 6930113 (Open Web Text)

Max Activating Token Index: 548

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.7829. Min Range: -2.7829

Max Act: 2.6545. Min Act: -0.1700

Data Index: 5476521 (Open Web Text)

Max Activating Token Index: 645

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.7829. Min Range: -2.7829

Max Act: 2.6603. Min Act: -0.1700

Data Index: 2077449 (Open Web Text)

Max Activating Token Index: 345

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.7829. Min Range: -2.7829

Max Act: 2.6594. Min Act: -0.1700

Data Index: 3116778 (Open Web Text)

Max Activating Token Index: 701

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.7829. Min Range: -2.7829

Max Act: 2.6739. Min Act: -0.1700

Data Index: 7604526 (Open Web Text)

Max Activating Token Index: 715

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.7829. Min Range: -2.7829

Max Act: 2.6795. Min Act: -0.1700

Data Index: 3614162 (Open Web Text)

Max Activating Token Index: 399

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.7829. Min Range: -2.7829

Max Act: 2.6270. Min Act: -0.1700

Data Index: 4354962 (Open Web Text)

Max Activating Token Index: 602

Click toggle to see full text

Truncated

Full Text #19