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

Dataset: Open Web Text

Neuron 1127 in Layer 2

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: 3.1860. Min Range: -3.1860

Max Act: 3.1860. Min Act: -0.1700

Data Index: 3046535 (Open Web Text)

Max Activating Token Index: 10

Text #1

Max Range: 3.1860. Min Range: -3.1860

Max Act: 3.1696. Min Act: -0.1700

Data Index: 669687 (Open Web Text)

Max Activating Token Index: 277

Text #2

Max Range: 3.1860. Min Range: -3.1860

Max Act: 3.1377. Min Act: -0.1700

Data Index: 5099859 (Open Web Text)

Max Activating Token Index: 882

Text #3

Max Range: 3.1860. Min Range: -3.1860

Max Act: 3.1021. Min Act: -0.1700

Data Index: 3439060 (Open Web Text)

Max Activating Token Index: 149

Text #4

Max Range: 3.1860. Min Range: -3.1860

Max Act: 3.0742. Min Act: -0.1700

Data Index: 795310 (Open Web Text)

Max Activating Token Index: 30

Text #5

Max Range: 3.1860. Min Range: -3.1860

Max Act: 3.0613. Min Act: -0.1700

Data Index: 3143368 (Open Web Text)

Max Activating Token Index: 622

Text #6

Max Range: 3.1860. Min Range: -3.1860

Max Act: 3.0456. Min Act: -0.1700

Data Index: 7036178 (Open Web Text)

Max Activating Token Index: 778

Text #7

Max Range: 3.1860. Min Range: -3.1860

Max Act: 3.0379. Min Act: -0.1700

Data Index: 7014862 (Open Web Text)

Max Activating Token Index: 142

Text #8

Max Range: 3.1860. Min Range: -3.1860

Max Act: 3.0596. Min Act: -0.1700

Data Index: 4725089 (Open Web Text)

Max Activating Token Index: 660

Text #9

Max Range: 3.1860. Min Range: -3.1860

Max Act: 2.9814. Min Act: -0.1700

Data Index: 4768118 (Open Web Text)

Max Activating Token Index: 799

Text #10

Max Range: 3.1860. Min Range: -3.1860

Max Act: 2.9639. Min Act: -0.1700

Data Index: 766944 (Open Web Text)

Max Activating Token Index: 236

Text #11

Max Range: 3.1860. Min Range: -3.1860

Max Act: 2.9427. Min Act: -0.1700

Data Index: 21586 (Open Web Text)

Max Activating Token Index: 68

Text #12

Max Range: 3.1860. Min Range: -3.1860

Max Act: 2.8809. Min Act: -0.1700

Data Index: 2034275 (Open Web Text)

Max Activating Token Index: 11

Text #13

Max Range: 3.1860. Min Range: -3.1860

Max Act: 2.8943. Min Act: -0.1700

Data Index: 86093 (Open Web Text)

Max Activating Token Index: 338

Text #14

Max Range: 3.1860. Min Range: -3.1860

Max Act: 2.8723. Min Act: -0.1700

Data Index: 4141123 (Open Web Text)

Max Activating Token Index: 145

Text #15

Max Range: 3.1860. Min Range: -3.1860

Max Act: 2.8699. Min Act: -0.1700

Data Index: 3439900 (Open Web Text)

Max Activating Token Index: 649

Text #16

Max Range: 3.1860. Min Range: -3.1860

Max Act: 2.8888. Min Act: -0.1700

Data Index: 3666329 (Open Web Text)

Max Activating Token Index: 882

Text #17

Max Range: 3.1860. Min Range: -3.1860

Max Act: 2.8519. Min Act: -0.1700

Data Index: 3735636 (Open Web Text)

Max Activating Token Index: 923

Text #18

Max Range: 3.1860. Min Range: -3.1860

Max Act: 2.8556. Min Act: -0.1700

Data Index: 7702959 (Open Web Text)

Max Activating Token Index: 76

Text #19

Max Range: 3.1860. Min Range: -3.1860

Max Act: 2.8629. Min Act: -0.1700

Data Index: 3327816 (Open Web Text)

Max Activating Token Index: 273