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

Dataset: Open Web Text

Neuron 2052 in Layer 4

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: 4.3504. Min Range: -4.3504

Max Act: 4.3504. Min Act: -0.1700

Data Index: 1757715 (Open Web Text)

Max Activating Token Index: 413

Text #1

Max Range: 4.3504. Min Range: -4.3504

Max Act: 4.2886. Min Act: -0.1700

Data Index: 1859590 (Open Web Text)

Max Activating Token Index: 489

Text #2

Max Range: 4.3504. Min Range: -4.3504

Max Act: 4.1921. Min Act: -0.1700

Data Index: 2817087 (Open Web Text)

Max Activating Token Index: 703

Text #3

Max Range: 4.3504. Min Range: -4.3504

Max Act: 4.1612. Min Act: -0.1700

Data Index: 2454595 (Open Web Text)

Max Activating Token Index: 146

Text #4

Max Range: 4.3504. Min Range: -4.3504

Max Act: 4.1600. Min Act: -0.1700

Data Index: 7437585 (Open Web Text)

Max Activating Token Index: 413

Text #5

Max Range: 4.3504. Min Range: -4.3504

Max Act: 4.1338. Min Act: -0.1700

Data Index: 3236437 (Open Web Text)

Max Activating Token Index: 125

Text #6

Max Range: 4.3504. Min Range: -4.3504

Max Act: 4.1033. Min Act: -0.1700

Data Index: 5215875 (Open Web Text)

Max Activating Token Index: 849

Text #7

Max Range: 4.3504. Min Range: -4.3504

Max Act: 4.1537. Min Act: -0.1700

Data Index: 2026127 (Open Web Text)

Max Activating Token Index: 602

Text #8

Max Range: 4.3504. Min Range: -4.3504

Max Act: 4.0579. Min Act: -0.1700

Data Index: 5259972 (Open Web Text)

Max Activating Token Index: 947

Text #9

Max Range: 4.3504. Min Range: -4.3504

Max Act: 4.0853. Min Act: -0.1700

Data Index: 1420800 (Open Web Text)

Max Activating Token Index: 886

Text #10

Max Range: 4.3504. Min Range: -4.3504

Max Act: 4.0789. Min Act: -0.1700

Data Index: 4585350 (Open Web Text)

Max Activating Token Index: 897

Text #11

Max Range: 4.3504. Min Range: -4.3504

Max Act: 3.9938. Min Act: -0.1700

Data Index: 2723838 (Open Web Text)

Max Activating Token Index: 668

Text #12

Max Range: 4.3504. Min Range: -4.3504

Max Act: 4.1025. Min Act: -0.1700

Data Index: 4056906 (Open Web Text)

Max Activating Token Index: 865

Text #13

Max Range: 4.3504. Min Range: -4.3504

Max Act: 4.0096. Min Act: -0.1700

Data Index: 157431 (Open Web Text)

Max Activating Token Index: 938

Text #14

Max Range: 4.3504. Min Range: -4.3504

Max Act: 4.0642. Min Act: -0.1700

Data Index: 1418450 (Open Web Text)

Max Activating Token Index: 994

Text #15

Max Range: 4.3504. Min Range: -4.3504

Max Act: 3.9638. Min Act: -0.1700

Data Index: 2809075 (Open Web Text)

Max Activating Token Index: 131

Text #16

Max Range: 4.3504. Min Range: -4.3504

Max Act: 3.9803. Min Act: -0.1700

Data Index: 2494628 (Open Web Text)

Max Activating Token Index: 312

Text #17

Max Range: 4.3504. Min Range: -4.3504

Max Act: 3.9715. Min Act: -0.1700

Data Index: 5307266 (Open Web Text)

Max Activating Token Index: 557

Text #18

Max Range: 4.3504. Min Range: -4.3504

Max Act: 3.9440. Min Act: -0.1700

Data Index: 3965682 (Open Web Text)

Max Activating Token Index: 148

Text #19

Max Range: 4.3504. Min Range: -4.3504

Max Act: 3.9899. Min Act: -0.1700

Data Index: 3915698 (Open Web Text)

Max Activating Token Index: 967