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

Dataset: Open Web Text

Neuron 2423 in Layer 0

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: 3.3285. Min Range: -3.3285

Max Act: 3.3171. Min Act: -0.1700

Data Index: 464109 (Open Web Text)

Max Activating Token Index: 685

Text #1

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.3285. Min Act: -0.1700

Data Index: 4250362 (Open Web Text)

Max Activating Token Index: 897

Text #2

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.2770. Min Act: -0.1700

Data Index: 8055715 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.2748. Min Act: -0.1700

Data Index: 3515325 (Open Web Text)

Max Activating Token Index: 692

Text #4

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.2622. Min Act: -0.1700

Data Index: 6605505 (Open Web Text)

Max Activating Token Index: 35

Text #5

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.2324. Min Act: -0.1700

Data Index: 3397776 (Open Web Text)

Max Activating Token Index: 14

Text #6

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.2087. Min Act: -0.1700

Data Index: 6562216 (Open Web Text)

Max Activating Token Index: 688

Text #7

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.2065. Min Act: -0.1700

Data Index: 5756506 (Open Web Text)

Max Activating Token Index: 946

Text #8

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.2182. Min Act: -0.1700

Data Index: 2003042 (Open Web Text)

Max Activating Token Index: 720

Text #9

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.2181. Min Act: -0.1700

Data Index: 5876728 (Open Web Text)

Max Activating Token Index: 740

Text #10

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.2217. Min Act: -0.1700

Data Index: 540159 (Open Web Text)

Max Activating Token Index: 696

Text #11

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.1993. Min Act: -0.1700

Data Index: 5214808 (Open Web Text)

Max Activating Token Index: 1022

Text #12

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.2036. Min Act: -0.1700

Data Index: 2992919 (Open Web Text)

Max Activating Token Index: 898

Text #13

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.1984. Min Act: -0.1700

Data Index: 1982619 (Open Web Text)

Max Activating Token Index: 784

Text #14

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.2067. Min Act: -0.1700

Data Index: 8117190 (Open Web Text)

Max Activating Token Index: 367

Text #15

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.1837. Min Act: -0.1700

Data Index: 5488550 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.1838. Min Act: -0.1700

Data Index: 7067477 (Open Web Text)

Max Activating Token Index: 695

Text #17

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.1855. Min Act: -0.1700

Data Index: 3565733 (Open Web Text)

Max Activating Token Index: 894

Text #18

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.1812. Min Act: -0.1700

Data Index: 6469130 (Open Web Text)

Max Activating Token Index: 150

Text #19

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.1784. Min Act: -0.1700

Data Index: 7470542 (Open Web Text)

Max Activating Token Index: 318