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

Dataset: Open Web Text

Neuron 3062 in Layer 1

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: 2.1073. Min Range: -2.1073

Max Act: 2.1073. Min Act: -0.1700

Data Index: 4354953 (Open Web Text)

Max Activating Token Index: 340

Text #1

Max Range: 2.1073. Min Range: -2.1073

Max Act: 2.1037. Min Act: -0.1700

Data Index: 7938485 (Open Web Text)

Max Activating Token Index: 553

Text #2

Max Range: 2.1073. Min Range: -2.1073

Max Act: 2.0838. Min Act: -0.1700

Data Index: 399775 (Open Web Text)

Max Activating Token Index: 414

Text #3

Max Range: 2.1073. Min Range: -2.1073

Max Act: 2.0885. Min Act: -0.1700

Data Index: 2760807 (Open Web Text)

Max Activating Token Index: 151

Text #4

Max Range: 2.1073. Min Range: -2.1073

Max Act: 2.0881. Min Act: -0.1700

Data Index: 8581896 (Open Web Text)

Max Activating Token Index: 320

Text #5

Max Range: 2.1073. Min Range: -2.1073

Max Act: 2.0814. Min Act: -0.1700

Data Index: 5734212 (Open Web Text)

Max Activating Token Index: 667

Text #6

Max Range: 2.1073. Min Range: -2.1073

Max Act: 2.0738. Min Act: -0.1700

Data Index: 6861093 (Open Web Text)

Max Activating Token Index: 526

Text #7

Max Range: 2.1073. Min Range: -2.1073

Max Act: 2.0684. Min Act: -0.1700

Data Index: 3530980 (Open Web Text)

Max Activating Token Index: 920

Text #8

Max Range: 2.1073. Min Range: -2.1073

Max Act: 2.0724. Min Act: -0.1700

Data Index: 8554184 (Open Web Text)

Max Activating Token Index: 951

Text #9

Max Range: 2.1073. Min Range: -2.1073

Max Act: 2.0482. Min Act: -0.1700

Data Index: 6165314 (Open Web Text)

Max Activating Token Index: 323

Text #10

Max Range: 2.1073. Min Range: -2.1073

Max Act: 2.0674. Min Act: -0.1700

Data Index: 5293369 (Open Web Text)

Max Activating Token Index: 465

Text #11

Max Range: 2.1073. Min Range: -2.1073

Max Act: 2.0464. Min Act: -0.1700

Data Index: 2723320 (Open Web Text)

Max Activating Token Index: 397

Text #12

Max Range: 2.1073. Min Range: -2.1073

Max Act: 2.0629. Min Act: -0.1700

Data Index: 1140956 (Open Web Text)

Max Activating Token Index: 644

Text #13

Max Range: 2.1073. Min Range: -2.1073

Max Act: 2.0691. Min Act: -0.1700

Data Index: 3981983 (Open Web Text)

Max Activating Token Index: 665

Text #14

Max Range: 2.1073. Min Range: -2.1073

Max Act: 2.0516. Min Act: -0.1700

Data Index: 7908617 (Open Web Text)

Max Activating Token Index: 911

Text #15

Max Range: 2.1073. Min Range: -2.1073

Max Act: 2.0535. Min Act: -0.1700

Data Index: 7854276 (Open Web Text)

Max Activating Token Index: 609

Text #16

Max Range: 2.1073. Min Range: -2.1073

Max Act: 2.0520. Min Act: -0.1700

Data Index: 7836360 (Open Web Text)

Max Activating Token Index: 787

Text #17

Max Range: 2.1073. Min Range: -2.1073

Max Act: 2.0643. Min Act: -0.1700

Data Index: 6498965 (Open Web Text)

Max Activating Token Index: 1008

Text #18

Max Range: 2.1073. Min Range: -2.1073

Max Act: 2.0507. Min Act: -0.1700

Data Index: 152110 (Open Web Text)

Max Activating Token Index: 502

Text #19

Max Range: 2.1073. Min Range: -2.1073

Max Act: 2.0294. Min Act: -0.1700

Data Index: 5598870 (Open Web Text)

Max Activating Token Index: 726