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

Dataset: Open Web Text

Neuron 2466 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: 5.0884. Min Range: -5.0884

Max Act: 5.0884. Min Act: -0.1700

Data Index: 2026722 (Open Web Text)

Max Activating Token Index: 648

Text #1

Max Range: 5.0884. Min Range: -5.0884

Max Act: 5.0269. Min Act: -0.1700

Data Index: 7934740 (Open Web Text)

Max Activating Token Index: 217

Text #2

Max Range: 5.0884. Min Range: -5.0884

Max Act: 4.9407. Min Act: -0.1700

Data Index: 2056368 (Open Web Text)

Max Activating Token Index: 679

Text #3

Max Range: 5.0884. Min Range: -5.0884

Max Act: 4.9744. Min Act: -0.1700

Data Index: 4355010 (Open Web Text)

Max Activating Token Index: 212

Text #4

Max Range: 5.0884. Min Range: -5.0884

Max Act: 4.9271. Min Act: -0.1700

Data Index: 2868015 (Open Web Text)

Max Activating Token Index: 911

Text #5

Max Range: 5.0884. Min Range: -5.0884

Max Act: 4.9355. Min Act: -0.1700

Data Index: 4394299 (Open Web Text)

Max Activating Token Index: 783

Text #6

Max Range: 5.0884. Min Range: -5.0884

Max Act: 4.9108. Min Act: -0.1700

Data Index: 5895302 (Open Web Text)

Max Activating Token Index: 172

Text #7

Max Range: 5.0884. Min Range: -5.0884

Max Act: 4.9056. Min Act: -0.1700

Data Index: 5805219 (Open Web Text)

Max Activating Token Index: 688

Text #8

Max Range: 5.0884. Min Range: -5.0884

Max Act: 4.8644. Min Act: -0.1700

Data Index: 2148598 (Open Web Text)

Max Activating Token Index: 659

Text #9

Max Range: 5.0884. Min Range: -5.0884

Max Act: 4.8662. Min Act: -0.1700

Data Index: 7596791 (Open Web Text)

Max Activating Token Index: 109

Text #10

Max Range: 5.0884. Min Range: -5.0884

Max Act: 4.8862. Min Act: -0.1700

Data Index: 8699570 (Open Web Text)

Max Activating Token Index: 298

Text #11

Max Range: 5.0884. Min Range: -5.0884

Max Act: 4.8212. Min Act: -0.1700

Data Index: 5057437 (Open Web Text)

Max Activating Token Index: 575

Text #12

Max Range: 5.0884. Min Range: -5.0884

Max Act: 4.7870. Min Act: -0.1700

Data Index: 1178157 (Open Web Text)

Max Activating Token Index: 620

Text #13

Max Range: 5.0884. Min Range: -5.0884

Max Act: 4.8335. Min Act: -0.1700

Data Index: 8280465 (Open Web Text)

Max Activating Token Index: 530

Text #14

Max Range: 5.0884. Min Range: -5.0884

Max Act: 4.7778. Min Act: -0.1700

Data Index: 4801841 (Open Web Text)

Max Activating Token Index: 885

Text #15

Max Range: 5.0884. Min Range: -5.0884

Max Act: 4.8097. Min Act: -0.1700

Data Index: 3155079 (Open Web Text)

Max Activating Token Index: 133

Text #16

Max Range: 5.0884. Min Range: -5.0884

Max Act: 4.8207. Min Act: -0.1700

Data Index: 6588204 (Open Web Text)

Max Activating Token Index: 1009

Text #17

Max Range: 5.0884. Min Range: -5.0884

Max Act: 4.8014. Min Act: -0.1700

Data Index: 942596 (Open Web Text)

Max Activating Token Index: 150

Text #18

Max Range: 5.0884. Min Range: -5.0884

Max Act: 4.8019. Min Act: -0.1700

Data Index: 3607438 (Open Web Text)

Max Activating Token Index: 728

Text #19

Max Range: 5.0884. Min Range: -5.0884

Max Act: 4.7661. Min Act: -0.1700

Data Index: 3112213 (Open Web Text)

Max Activating Token Index: 467