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

Dataset: Open Web Text

Neuron 463 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: 4.0357. Min Range: -4.0357

Max Act: 4.0357. Min Act: -0.1700

Data Index: 8557120 (Open Web Text)

Max Activating Token Index: 496

Text #1

Max Range: 4.0357. Min Range: -4.0357

Max Act: 3.9340. Min Act: -0.1700

Data Index: 3046918 (Open Web Text)

Max Activating Token Index: 201

Text #2

Max Range: 4.0357. Min Range: -4.0357

Max Act: 3.9673. Min Act: -0.1700

Data Index: 7992899 (Open Web Text)

Max Activating Token Index: 9

Text #3

Max Range: 4.0357. Min Range: -4.0357

Max Act: 3.9698. Min Act: -0.1700

Data Index: 4467800 (Open Web Text)

Max Activating Token Index: 18

Text #4

Max Range: 4.0357. Min Range: -4.0357

Max Act: 3.9505. Min Act: -0.1700

Data Index: 2003941 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 4.0357. Min Range: -4.0357

Max Act: 3.9324. Min Act: -0.1700

Data Index: 5349647 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 4.0357. Min Range: -4.0357

Max Act: 3.9385. Min Act: -0.1700

Data Index: 5954097 (Open Web Text)

Max Activating Token Index: 458

Text #7

Max Range: 4.0357. Min Range: -4.0357

Max Act: 3.9393. Min Act: -0.1700

Data Index: 3635305 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 4.0357. Min Range: -4.0357

Max Act: 3.9699. Min Act: -0.1700

Data Index: 8295851 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 4.0357. Min Range: -4.0357

Max Act: 3.9411. Min Act: -0.1700

Data Index: 3998884 (Open Web Text)

Max Activating Token Index: 558

Text #10

Max Range: 4.0357. Min Range: -4.0357

Max Act: 3.9512. Min Act: -0.1700

Data Index: 2918467 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 4.0357. Min Range: -4.0357

Max Act: 3.9113. Min Act: -0.1700

Data Index: 546305 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 4.0357. Min Range: -4.0357

Max Act: 3.9022. Min Act: -0.1700

Data Index: 2784149 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 4.0357. Min Range: -4.0357

Max Act: 3.9062. Min Act: -0.1700

Data Index: 8546967 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 4.0357. Min Range: -4.0357

Max Act: 3.9038. Min Act: -0.1700

Data Index: 8419723 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 4.0357. Min Range: -4.0357

Max Act: 3.9022. Min Act: -0.1700

Data Index: 1874463 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.0357. Min Range: -4.0357

Max Act: 3.8644. Min Act: -0.1700

Data Index: 3408021 (Open Web Text)

Max Activating Token Index: 818

Text #17

Max Range: 4.0357. Min Range: -4.0357

Max Act: 3.9193. Min Act: -0.1700

Data Index: 4623950 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 4.0357. Min Range: -4.0357

Max Act: 3.9279. Min Act: -0.1700

Data Index: 1876719 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 4.0357. Min Range: -4.0357

Max Act: 3.8889. Min Act: -0.1700

Data Index: 4517592 (Open Web Text)

Max Activating Token Index: 7