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

Dataset: Open Web Text

Neuron 1373 in Layer 3

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: 4.0254. Min Range: -4.0254

Max Act: 4.0254. Min Act: -0.1700

Data Index: 7285884 (Open Web Text)

Max Activating Token Index: 1012

Text #1

Max Range: 4.0254. Min Range: -4.0254

Max Act: 4.0191. Min Act: -0.1700

Data Index: 4952510 (Open Web Text)

Max Activating Token Index: 771

Text #2

Max Range: 4.0254. Min Range: -4.0254

Max Act: 3.8565. Min Act: -0.1700

Data Index: 2917639 (Open Web Text)

Max Activating Token Index: 922

Text #3

Max Range: 4.0254. Min Range: -4.0254

Max Act: 3.7864. Min Act: -0.1700

Data Index: 5690541 (Open Web Text)

Max Activating Token Index: 752

Text #4

Max Range: 4.0254. Min Range: -4.0254

Max Act: 3.7473. Min Act: -0.1700

Data Index: 2493303 (Open Web Text)

Max Activating Token Index: 807

Text #5

Max Range: 4.0254. Min Range: -4.0254

Max Act: 3.7293. Min Act: -0.1700

Data Index: 8661648 (Open Web Text)

Max Activating Token Index: 720

Text #6

Max Range: 4.0254. Min Range: -4.0254

Max Act: 3.7466. Min Act: -0.1700

Data Index: 7628247 (Open Web Text)

Max Activating Token Index: 854

Text #7

Max Range: 4.0254. Min Range: -4.0254

Max Act: 3.7150. Min Act: -0.1700

Data Index: 1559489 (Open Web Text)

Max Activating Token Index: 742

Text #8

Max Range: 4.0254. Min Range: -4.0254

Max Act: 3.7385. Min Act: -0.1700

Data Index: 7754808 (Open Web Text)

Max Activating Token Index: 850

Text #9

Max Range: 4.0254. Min Range: -4.0254

Max Act: 3.6824. Min Act: -0.1700

Data Index: 4224462 (Open Web Text)

Max Activating Token Index: 861

Text #10

Max Range: 4.0254. Min Range: -4.0254

Max Act: 3.7095. Min Act: -0.1700

Data Index: 4623145 (Open Web Text)

Max Activating Token Index: 983

Text #11

Max Range: 4.0254. Min Range: -4.0254

Max Act: 3.6560. Min Act: -0.1700

Data Index: 6384964 (Open Web Text)

Max Activating Token Index: 913

Text #12

Max Range: 4.0254. Min Range: -4.0254

Max Act: 3.7081. Min Act: -0.1700

Data Index: 6619893 (Open Web Text)

Max Activating Token Index: 965

Text #13

Max Range: 4.0254. Min Range: -4.0254

Max Act: 3.6577. Min Act: -0.1700

Data Index: 5447526 (Open Web Text)

Max Activating Token Index: 769

Text #14

Max Range: 4.0254. Min Range: -4.0254

Max Act: 3.6702. Min Act: -0.1700

Data Index: 7343942 (Open Web Text)

Max Activating Token Index: 670

Text #15

Max Range: 4.0254. Min Range: -4.0254

Max Act: 3.6737. Min Act: -0.1700

Data Index: 6781070 (Open Web Text)

Max Activating Token Index: 818

Text #16

Max Range: 4.0254. Min Range: -4.0254

Max Act: 3.6206. Min Act: -0.1700

Data Index: 4417307 (Open Web Text)

Max Activating Token Index: 864

Text #17

Max Range: 4.0254. Min Range: -4.0254

Max Act: 3.6581. Min Act: -0.1700

Data Index: 2572813 (Open Web Text)

Max Activating Token Index: 711

Text #18

Max Range: 4.0254. Min Range: -4.0254

Max Act: 3.6757. Min Act: -0.1700

Data Index: 5487704 (Open Web Text)

Max Activating Token Index: 377

Text #19

Max Range: 4.0254. Min Range: -4.0254

Max Act: 3.6049. Min Act: -0.1700

Data Index: 6932834 (Open Web Text)

Max Activating Token Index: 846