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

Dataset: Open Web Text

Neuron 1641 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: 4.1449. Min Range: -4.1449

Max Act: 4.1449. Min Act: -0.1700

Data Index: 6119581 (Open Web Text)

Max Activating Token Index: 974

Text #1

Max Range: 4.1449. Min Range: -4.1449

Max Act: 4.0806. Min Act: -0.1700

Data Index: 6345963 (Open Web Text)

Max Activating Token Index: 523

Text #2

Max Range: 4.1449. Min Range: -4.1449

Max Act: 4.0675. Min Act: -0.1700

Data Index: 5861709 (Open Web Text)

Max Activating Token Index: 323

Text #3

Max Range: 4.1449. Min Range: -4.1449

Max Act: 4.0327. Min Act: -0.1700

Data Index: 7724342 (Open Web Text)

Max Activating Token Index: 99

Text #4

Max Range: 4.1449. Min Range: -4.1449

Max Act: 4.0056. Min Act: -0.1700

Data Index: 1866448 (Open Web Text)

Max Activating Token Index: 239

Text #5

Max Range: 4.1449. Min Range: -4.1449

Max Act: 4.0362. Min Act: -0.1700

Data Index: 5521555 (Open Web Text)

Max Activating Token Index: 908

Text #6

Max Range: 4.1449. Min Range: -4.1449

Max Act: 3.9875. Min Act: -0.1700

Data Index: 3720880 (Open Web Text)

Max Activating Token Index: 276

Text #7

Max Range: 4.1449. Min Range: -4.1449

Max Act: 4.0271. Min Act: -0.1700

Data Index: 86378 (Open Web Text)

Max Activating Token Index: 220

Text #8

Max Range: 4.1449. Min Range: -4.1449

Max Act: 3.9919. Min Act: -0.1700

Data Index: 7419639 (Open Web Text)

Max Activating Token Index: 351

Text #9

Max Range: 4.1449. Min Range: -4.1449

Max Act: 3.9470. Min Act: -0.1700

Data Index: 8518290 (Open Web Text)

Max Activating Token Index: 405

Text #10

Max Range: 4.1449. Min Range: -4.1449

Max Act: 3.9454. Min Act: -0.1700

Data Index: 6860469 (Open Web Text)

Max Activating Token Index: 604

Text #11

Max Range: 4.1449. Min Range: -4.1449

Max Act: 3.9149. Min Act: -0.1700

Data Index: 6977690 (Open Web Text)

Max Activating Token Index: 356

Text #12

Max Range: 4.1449. Min Range: -4.1449

Max Act: 3.9142. Min Act: -0.1700

Data Index: 2603738 (Open Web Text)

Max Activating Token Index: 291

Text #13

Max Range: 4.1449. Min Range: -4.1449

Max Act: 3.9180. Min Act: -0.1700

Data Index: 6102118 (Open Web Text)

Max Activating Token Index: 775

Text #14

Max Range: 4.1449. Min Range: -4.1449

Max Act: 3.9286. Min Act: -0.1700

Data Index: 5998573 (Open Web Text)

Max Activating Token Index: 198

Text #15

Max Range: 4.1449. Min Range: -4.1449

Max Act: 3.8884. Min Act: -0.1700

Data Index: 1596276 (Open Web Text)

Max Activating Token Index: 182

Text #16

Max Range: 4.1449. Min Range: -4.1449

Max Act: 3.9112. Min Act: -0.1700

Data Index: 5156633 (Open Web Text)

Max Activating Token Index: 753

Text #17

Max Range: 4.1449. Min Range: -4.1449

Max Act: 3.8987. Min Act: -0.1700

Data Index: 5435671 (Open Web Text)

Max Activating Token Index: 566

Text #18

Max Range: 4.1449. Min Range: -4.1449

Max Act: 3.9252. Min Act: -0.1700

Data Index: 3911428 (Open Web Text)

Max Activating Token Index: 413

Text #19

Max Range: 4.1449. Min Range: -4.1449

Max Act: 3.9031. Min Act: -0.1700

Data Index: 1122093 (Open Web Text)

Max Activating Token Index: 924