< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 1645 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: 2.9652. Min Range: -2.9652

Max Act: 2.9652. Min Act: -0.1700

Data Index: 712543 (Open Web Text)

Max Activating Token Index: 202

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.9652. Min Range: -2.9652

Max Act: 2.9245. Min Act: -0.1700

Data Index: 5904234 (Open Web Text)

Max Activating Token Index: 48

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.9652. Min Range: -2.9652

Max Act: 2.9274. Min Act: -0.1700

Data Index: 5834076 (Open Web Text)

Max Activating Token Index: 414

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.9652. Min Range: -2.9652

Max Act: 2.9236. Min Act: -0.1700

Data Index: 8305614 (Open Web Text)

Max Activating Token Index: 435

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.9652. Min Range: -2.9652

Max Act: 2.9232. Min Act: -0.1700

Data Index: 5798941 (Open Web Text)

Max Activating Token Index: 363

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.9652. Min Range: -2.9652

Max Act: 2.9094. Min Act: -0.1700

Data Index: 1157891 (Open Web Text)

Max Activating Token Index: 69

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.9652. Min Range: -2.9652

Max Act: 2.8933. Min Act: -0.1700

Data Index: 5617717 (Open Web Text)

Max Activating Token Index: 980

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.9652. Min Range: -2.9652

Max Act: 2.8985. Min Act: -0.1700

Data Index: 3369249 (Open Web Text)

Max Activating Token Index: 276

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.9652. Min Range: -2.9652

Max Act: 2.8792. Min Act: -0.1700

Data Index: 5334910 (Open Web Text)

Max Activating Token Index: 951

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.9652. Min Range: -2.9652

Max Act: 2.8790. Min Act: -0.1700

Data Index: 4358557 (Open Web Text)

Max Activating Token Index: 190

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.9652. Min Range: -2.9652

Max Act: 2.8634. Min Act: -0.1700

Data Index: 3565348 (Open Web Text)

Max Activating Token Index: 891

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.9652. Min Range: -2.9652

Max Act: 2.8650. Min Act: -0.1700

Data Index: 6536426 (Open Web Text)

Max Activating Token Index: 24

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.9652. Min Range: -2.9652

Max Act: 2.8441. Min Act: -0.1700

Data Index: 3962411 (Open Web Text)

Max Activating Token Index: 887

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.9652. Min Range: -2.9652

Max Act: 2.8582. Min Act: -0.1700

Data Index: 4696017 (Open Web Text)

Max Activating Token Index: 349

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.9652. Min Range: -2.9652

Max Act: 2.8701. Min Act: -0.1700

Data Index: 3269705 (Open Web Text)

Max Activating Token Index: 541

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.9652. Min Range: -2.9652

Max Act: 2.8504. Min Act: -0.1700

Data Index: 4489808 (Open Web Text)

Max Activating Token Index: 348

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.9652. Min Range: -2.9652

Max Act: 2.8373. Min Act: -0.1700

Data Index: 1656453 (Open Web Text)

Max Activating Token Index: 752

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.9652. Min Range: -2.9652

Max Act: 2.8475. Min Act: -0.1700

Data Index: 1380266 (Open Web Text)

Max Activating Token Index: 117

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.9652. Min Range: -2.9652

Max Act: 2.8436. Min Act: -0.1700

Data Index: 6714883 (Open Web Text)

Max Activating Token Index: 517

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.9652. Min Range: -2.9652

Max Act: 2.8326. Min Act: -0.1700

Data Index: 7288795 (Open Web Text)

Max Activating Token Index: 568

Click toggle to see full text

Truncated

Full Text #19