< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 423 in Layer 2

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: 2.3346. Min Range: -2.3346

Max Act: 2.3346. Min Act: -0.1700

Data Index: 7038678 (Open Web Text)

Max Activating Token Index: 918

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.3346. Min Range: -2.3346

Max Act: 2.2878. Min Act: -0.1700

Data Index: 2543079 (Open Web Text)

Max Activating Token Index: 830

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.3346. Min Range: -2.3346

Max Act: 2.2665. Min Act: -0.1698

Data Index: 3704432 (Open Web Text)

Max Activating Token Index: 327

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.3346. Min Range: -2.3346

Max Act: 2.2651. Min Act: -0.1700

Data Index: 2713837 (Open Web Text)

Max Activating Token Index: 462

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.3346. Min Range: -2.3346

Max Act: 2.2581. Min Act: -0.1700

Data Index: 2485046 (Open Web Text)

Max Activating Token Index: 813

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.3346. Min Range: -2.3346

Max Act: 2.2775. Min Act: -0.1700

Data Index: 809007 (Open Web Text)

Max Activating Token Index: 258

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.3346. Min Range: -2.3346

Max Act: 2.2556. Min Act: -0.1700

Data Index: 6357655 (Open Web Text)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.3346. Min Range: -2.3346

Max Act: 2.2738. Min Act: -0.1700

Data Index: 6590790 (Open Web Text)

Max Activating Token Index: 342

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.3346. Min Range: -2.3346

Max Act: 2.2602. Min Act: -0.1700

Data Index: 3343940 (Open Web Text)

Max Activating Token Index: 979

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.3346. Min Range: -2.3346

Max Act: 2.2588. Min Act: -0.1700

Data Index: 1515574 (Open Web Text)

Max Activating Token Index: 957

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.3346. Min Range: -2.3346

Max Act: 2.2190. Min Act: -0.1700

Data Index: 4719762 (Open Web Text)

Max Activating Token Index: 930

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.3346. Min Range: -2.3346

Max Act: 2.2317. Min Act: -0.1700

Data Index: 8299303 (Open Web Text)

Max Activating Token Index: 16

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.3346. Min Range: -2.3346

Max Act: 2.2468. Min Act: -0.1700

Data Index: 2519611 (Open Web Text)

Max Activating Token Index: 658

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.3346. Min Range: -2.3346

Max Act: 2.2338. Min Act: -0.1700

Data Index: 2579300 (Open Web Text)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.3346. Min Range: -2.3346

Max Act: 2.2056. Min Act: -0.1700

Data Index: 7648137 (Open Web Text)

Max Activating Token Index: 188

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.3346. Min Range: -2.3346

Max Act: 2.2213. Min Act: -0.1700

Data Index: 3476677 (Open Web Text)

Max Activating Token Index: 132

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.3346. Min Range: -2.3346

Max Act: 2.2307. Min Act: -0.1700

Data Index: 2579308 (Open Web Text)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.3346. Min Range: -2.3346

Max Act: 2.2319. Min Act: -0.1700

Data Index: 2150771 (Open Web Text)

Max Activating Token Index: 50

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.3346. Min Range: -2.3346

Max Act: 2.2099. Min Act: -0.1700

Data Index: 3702264 (Open Web Text)

Max Activating Token Index: 679

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.3346. Min Range: -2.3346

Max Act: 2.2077. Min Act: -0.1700

Data Index: 5005546 (Open Web Text)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #19