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

Dataset: Open Web Text

Neuron 792 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: 3.0504. Min Range: -3.0504

Max Act: 3.0504. Min Act: -0.1700

Data Index: 446733 (Open Web Text)

Max Activating Token Index: 322

Text #1

Max Range: 3.0504. Min Range: -3.0504

Max Act: 2.9375. Min Act: -0.1700

Data Index: 3374148 (Open Web Text)

Max Activating Token Index: 657

Text #2

Max Range: 3.0504. Min Range: -3.0504

Max Act: 2.8485. Min Act: -0.1700

Data Index: 7757853 (Open Web Text)

Max Activating Token Index: 772

Text #3

Max Range: 3.0504. Min Range: -3.0504

Max Act: 2.8692. Min Act: -0.1700

Data Index: 4454660 (Open Web Text)

Max Activating Token Index: 588

Text #4

Max Range: 3.0504. Min Range: -3.0504

Max Act: 2.8491. Min Act: -0.1700

Data Index: 7300484 (Open Web Text)

Max Activating Token Index: 946

Text #5

Max Range: 3.0504. Min Range: -3.0504

Max Act: 2.8399. Min Act: -0.1700

Data Index: 3844756 (Open Web Text)

Max Activating Token Index: 705

Text #6

Max Range: 3.0504. Min Range: -3.0504

Max Act: 2.8242. Min Act: -0.1700

Data Index: 609838 (Open Web Text)

Max Activating Token Index: 708

Text #7

Max Range: 3.0504. Min Range: -3.0504

Max Act: 2.8173. Min Act: -0.1700

Data Index: 5520844 (Open Web Text)

Max Activating Token Index: 131

Text #8

Max Range: 3.0504. Min Range: -3.0504

Max Act: 2.8215. Min Act: -0.1700

Data Index: 2236972 (Open Web Text)

Max Activating Token Index: 780

Text #9

Max Range: 3.0504. Min Range: -3.0504

Max Act: 2.8020. Min Act: -0.1700

Data Index: 4670794 (Open Web Text)

Max Activating Token Index: 543

Text #10

Max Range: 3.0504. Min Range: -3.0504

Max Act: 2.8053. Min Act: -0.1700

Data Index: 5402303 (Open Web Text)

Max Activating Token Index: 473

Text #11

Max Range: 3.0504. Min Range: -3.0504

Max Act: 2.7946. Min Act: -0.1700

Data Index: 4355965 (Open Web Text)

Max Activating Token Index: 269

Text #12

Max Range: 3.0504. Min Range: -3.0504

Max Act: 2.8063. Min Act: -0.1700

Data Index: 6666500 (Open Web Text)

Max Activating Token Index: 686

Text #13

Max Range: 3.0504. Min Range: -3.0504

Max Act: 2.7975. Min Act: -0.1700

Data Index: 4364053 (Open Web Text)

Max Activating Token Index: 78

Text #14

Max Range: 3.0504. Min Range: -3.0504

Max Act: 2.8198. Min Act: -0.1700

Data Index: 7786100 (Open Web Text)

Max Activating Token Index: 543

Text #15

Max Range: 3.0504. Min Range: -3.0504

Max Act: 2.7706. Min Act: -0.1700

Data Index: 1964715 (Open Web Text)

Max Activating Token Index: 817

Text #16

Max Range: 3.0504. Min Range: -3.0504

Max Act: 2.7766. Min Act: -0.1700

Data Index: 2776510 (Open Web Text)

Max Activating Token Index: 953

Text #17

Max Range: 3.0504. Min Range: -3.0504

Max Act: 2.7989. Min Act: -0.1700

Data Index: 5334302 (Open Web Text)

Max Activating Token Index: 444

Text #18

Max Range: 3.0504. Min Range: -3.0504

Max Act: 2.7882. Min Act: -0.1700

Data Index: 4383098 (Open Web Text)

Max Activating Token Index: 960

Text #19

Max Range: 3.0504. Min Range: -3.0504

Max Act: 2.7864. Min Act: -0.1700

Data Index: 2872598 (Open Web Text)

Max Activating Token Index: 279