< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 1467 in Layer 4

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: 2.4389. Min Range: -2.4389

Max Act: 2.4389. Min Act: -0.1700

Data Index: 7410032 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.4389. Min Range: -2.4389

Max Act: 2.3854. Min Act: -0.1700

Data Index: 7225493 (Open Web Text)

Max Activating Token Index: 818

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.4389. Min Range: -2.4389

Max Act: 2.4178. Min Act: -0.1700

Data Index: 5649373 (Open Web Text)

Max Activating Token Index: 217

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.4389. Min Range: -2.4389

Max Act: 2.3639. Min Act: -0.1700

Data Index: 5087291 (Open Web Text)

Max Activating Token Index: 10

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.4389. Min Range: -2.4389

Max Act: 2.3438. Min Act: -0.1700

Data Index: 6257879 (Open Web Text)

Max Activating Token Index: 403

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.4389. Min Range: -2.4389

Max Act: 2.3357. Min Act: -0.1700

Data Index: 7456755 (Open Web Text)

Max Activating Token Index: 759

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.4389. Min Range: -2.4389

Max Act: 2.3307. Min Act: -0.1700

Data Index: 3186896 (Open Web Text)

Max Activating Token Index: 614

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.4389. Min Range: -2.4389

Max Act: 2.3487. Min Act: -0.1700

Data Index: 4846214 (Open Web Text)

Max Activating Token Index: 624

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.4389. Min Range: -2.4389

Max Act: 2.3343. Min Act: -0.1700

Data Index: 1755669 (Open Web Text)

Max Activating Token Index: 230

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.4389. Min Range: -2.4389

Max Act: 2.3373. Min Act: -0.1700

Data Index: 7121370 (Open Web Text)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.4389. Min Range: -2.4389

Max Act: 2.3640. Min Act: -0.1700

Data Index: 6593833 (Open Web Text)

Max Activating Token Index: 546

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.4389. Min Range: -2.4389

Max Act: 2.3326. Min Act: -0.1700

Data Index: 7146083 (Open Web Text)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.4389. Min Range: -2.4389

Max Act: 2.3196. Min Act: -0.1700

Data Index: 6078318 (Open Web Text)

Max Activating Token Index: 528

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.4389. Min Range: -2.4389

Max Act: 2.3192. Min Act: -0.1700

Data Index: 4803708 (Open Web Text)

Max Activating Token Index: 878

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.4389. Min Range: -2.4389

Max Act: 2.3156. Min Act: -0.1700

Data Index: 82223 (Open Web Text)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.4389. Min Range: -2.4389

Max Act: 2.3142. Min Act: -0.1700

Data Index: 4695610 (Open Web Text)

Max Activating Token Index: 294

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.4389. Min Range: -2.4389

Max Act: 2.3143. Min Act: -0.1700

Data Index: 6120477 (Open Web Text)

Max Activating Token Index: 414

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.4389. Min Range: -2.4389

Max Act: 2.3184. Min Act: -0.1700

Data Index: 2532038 (Open Web Text)

Max Activating Token Index: 321

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.4389. Min Range: -2.4389

Max Act: 2.3067. Min Act: -0.1700

Data Index: 1404875 (Open Web Text)

Max Activating Token Index: 972

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.4389. Min Range: -2.4389

Max Act: 2.2908. Min Act: -0.1700

Data Index: 6120817 (Open Web Text)

Max Activating Token Index: 788

Click toggle to see full text

Truncated

Full Text #19