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

Dataset: Open Web Text

Neuron 472 in Layer 6

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: 4.5283. Min Range: -4.5283

Max Act: 4.5283. Min Act: -0.1700

Data Index: 2057895 (Open Web Text)

Max Activating Token Index: 351

Text #1

Max Range: 4.5283. Min Range: -4.5283

Max Act: 4.0333. Min Act: -0.1700

Data Index: 8195782 (Open Web Text)

Max Activating Token Index: 556

Text #2

Max Range: 4.5283. Min Range: -4.5283

Max Act: 3.9392. Min Act: -0.1700

Data Index: 1356217 (Open Web Text)

Max Activating Token Index: 894

Text #3

Max Range: 4.5283. Min Range: -4.5283

Max Act: 3.5411. Min Act: -0.1700

Data Index: 260657 (Open Web Text)

Max Activating Token Index: 478

Text #4

Max Range: 4.5283. Min Range: -4.5283

Max Act: 3.3996. Min Act: -0.1700

Data Index: 2116693 (Open Web Text)

Max Activating Token Index: 463

Text #5

Max Range: 4.5283. Min Range: -4.5283

Max Act: 3.4515. Min Act: -0.1700

Data Index: 7132738 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 4.5283. Min Range: -4.5283

Max Act: 3.4164. Min Act: -0.1700

Data Index: 585790 (Open Web Text)

Max Activating Token Index: 183

Text #7

Max Range: 4.5283. Min Range: -4.5283

Max Act: 3.3906. Min Act: -0.1700

Data Index: 7616330 (Open Web Text)

Max Activating Token Index: 314

Text #8

Max Range: 4.5283. Min Range: -4.5283

Max Act: 3.3865. Min Act: -0.1700

Data Index: 4317314 (Open Web Text)

Max Activating Token Index: 194

Text #9

Max Range: 4.5283. Min Range: -4.5283

Max Act: 3.3533. Min Act: -0.1700

Data Index: 7056759 (Open Web Text)

Max Activating Token Index: 14

Text #10

Max Range: 4.5283. Min Range: -4.5283

Max Act: 3.2952. Min Act: -0.1700

Data Index: 7337859 (Open Web Text)

Max Activating Token Index: 529

Text #11

Max Range: 4.5283. Min Range: -4.5283

Max Act: 3.3012. Min Act: -0.1700

Data Index: 6491092 (Open Web Text)

Max Activating Token Index: 496

Text #12

Max Range: 4.5283. Min Range: -4.5283

Max Act: 3.2740. Min Act: -0.1700

Data Index: 8104020 (Open Web Text)

Max Activating Token Index: 344

Text #13

Max Range: 4.5283. Min Range: -4.5283

Max Act: 3.2697. Min Act: -0.1700

Data Index: 8467948 (Open Web Text)

Max Activating Token Index: 516

Text #14

Max Range: 4.5283. Min Range: -4.5283

Max Act: 3.2782. Min Act: -0.1700

Data Index: 5834775 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 4.5283. Min Range: -4.5283

Max Act: 3.2615. Min Act: -0.1700

Data Index: 1664282 (Open Web Text)

Max Activating Token Index: 407

Text #16

Max Range: 4.5283. Min Range: -4.5283

Max Act: 3.2391. Min Act: -0.1700

Data Index: 1582189 (Open Web Text)

Max Activating Token Index: 568

Text #17

Max Range: 4.5283. Min Range: -4.5283

Max Act: 3.2460. Min Act: -0.1700

Data Index: 6028492 (Open Web Text)

Max Activating Token Index: 892

Text #18

Max Range: 4.5283. Min Range: -4.5283

Max Act: 3.2635. Min Act: -0.1700

Data Index: 8130011 (Open Web Text)

Max Activating Token Index: 381

Text #19

Max Range: 4.5283. Min Range: -4.5283

Max Act: 3.1895. Min Act: -0.1700

Data Index: 7907407 (Open Web Text)

Max Activating Token Index: 355