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

Dataset: Open Web Text

Neuron 1178 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: 5.0571. Min Range: -5.0571

Max Act: 5.0571. Min Act: -0.1700

Data Index: 6638290 (Open Web Text)

Max Activating Token Index: 57

Text #1

Max Range: 5.0571. Min Range: -5.0571

Max Act: 4.9991. Min Act: -0.1700

Data Index: 4865494 (Open Web Text)

Max Activating Token Index: 608

Text #2

Max Range: 5.0571. Min Range: -5.0571

Max Act: 4.9937. Min Act: -0.1700

Data Index: 7495294 (Open Web Text)

Max Activating Token Index: 525

Text #3

Max Range: 5.0571. Min Range: -5.0571

Max Act: 4.9651. Min Act: -0.1700

Data Index: 2677887 (Open Web Text)

Max Activating Token Index: 74

Text #4

Max Range: 5.0571. Min Range: -5.0571

Max Act: 4.9431. Min Act: -0.1700

Data Index: 4248571 (Open Web Text)

Max Activating Token Index: 669

Text #5

Max Range: 5.0571. Min Range: -5.0571

Max Act: 4.9426. Min Act: -0.1700

Data Index: 904144 (Open Web Text)

Max Activating Token Index: 985

Text #6

Max Range: 5.0571. Min Range: -5.0571

Max Act: 4.9144. Min Act: -0.1700

Data Index: 5081629 (Open Web Text)

Max Activating Token Index: 1022

Text #7

Max Range: 5.0571. Min Range: -5.0571

Max Act: 4.9090. Min Act: -0.1700

Data Index: 7233936 (Open Web Text)

Max Activating Token Index: 627

Text #8

Max Range: 5.0571. Min Range: -5.0571

Max Act: 4.9183. Min Act: -0.1700

Data Index: 1821902 (Open Web Text)

Max Activating Token Index: 93

Text #9

Max Range: 5.0571. Min Range: -5.0571

Max Act: 4.9097. Min Act: -0.1700

Data Index: 4929671 (Open Web Text)

Max Activating Token Index: 632

Text #10

Max Range: 5.0571. Min Range: -5.0571

Max Act: 4.9012. Min Act: -0.1700

Data Index: 3250189 (Open Web Text)

Max Activating Token Index: 1007

Text #11

Max Range: 5.0571. Min Range: -5.0571

Max Act: 4.8853. Min Act: -0.1700

Data Index: 2536785 (Open Web Text)

Max Activating Token Index: 456

Text #12

Max Range: 5.0571. Min Range: -5.0571

Max Act: 4.8816. Min Act: -0.1700

Data Index: 7116961 (Open Web Text)

Max Activating Token Index: 849

Text #13

Max Range: 5.0571. Min Range: -5.0571

Max Act: 4.8883. Min Act: -0.1700

Data Index: 4996133 (Open Web Text)

Max Activating Token Index: 508

Text #14

Max Range: 5.0571. Min Range: -5.0571

Max Act: 4.8688. Min Act: -0.1700

Data Index: 3338254 (Open Web Text)

Max Activating Token Index: 705

Text #15

Max Range: 5.0571. Min Range: -5.0571

Max Act: 4.8843. Min Act: -0.1700

Data Index: 4046187 (Open Web Text)

Max Activating Token Index: 282

Text #16

Max Range: 5.0571. Min Range: -5.0571

Max Act: 4.8772. Min Act: -0.1700

Data Index: 8197784 (Open Web Text)

Max Activating Token Index: 583

Text #17

Max Range: 5.0571. Min Range: -5.0571

Max Act: 4.8697. Min Act: -0.1700

Data Index: 7812001 (Open Web Text)

Max Activating Token Index: 663

Text #18

Max Range: 5.0571. Min Range: -5.0571

Max Act: 4.8667. Min Act: -0.1700

Data Index: 1179796 (Open Web Text)

Max Activating Token Index: 912

Text #19

Max Range: 5.0571. Min Range: -5.0571

Max Act: 4.8540. Min Act: -0.1700

Data Index: 3829654 (Open Web Text)

Max Activating Token Index: 500