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

Dataset: Open Web Text

Neuron 2722 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: 3.0563. Min Range: -3.0563

Max Act: 3.0563. Min Act: -0.1700

Data Index: 5201060 (Open Web Text)

Max Activating Token Index: 503

Text #1

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.9752. Min Act: -0.1700

Data Index: 1275240 (Open Web Text)

Max Activating Token Index: 806

Text #2

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.8571. Min Act: -0.1700

Data Index: 3526573 (Open Web Text)

Max Activating Token Index: 558

Text #3

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.8797. Min Act: -0.1700

Data Index: 2670616 (Open Web Text)

Max Activating Token Index: 1003

Text #4

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.8558. Min Act: -0.1700

Data Index: 6871855 (Open Web Text)

Max Activating Token Index: 390

Text #5

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.8060. Min Act: -0.1700

Data Index: 5111924 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.8360. Min Act: -0.1700

Data Index: 3385120 (Open Web Text)

Max Activating Token Index: 670

Text #7

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.8202. Min Act: -0.1700

Data Index: 8533255 (Open Web Text)

Max Activating Token Index: 543

Text #8

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.8166. Min Act: -0.1700

Data Index: 6408398 (Open Web Text)

Max Activating Token Index: 391

Text #9

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.7829. Min Act: -0.1700

Data Index: 7539592 (Open Web Text)

Max Activating Token Index: 16

Text #10

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.7824. Min Act: -0.1700

Data Index: 3283976 (Open Web Text)

Max Activating Token Index: 686

Text #11

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.7897. Min Act: -0.1700

Data Index: 5320722 (Open Web Text)

Max Activating Token Index: 634

Text #12

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.7687. Min Act: -0.1700

Data Index: 5985324 (Open Web Text)

Max Activating Token Index: 250

Text #13

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.7841. Min Act: -0.1700

Data Index: 6700794 (Open Web Text)

Max Activating Token Index: 36

Text #14

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.7828. Min Act: -0.1700

Data Index: 7362880 (Open Web Text)

Max Activating Token Index: 843

Text #15

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.7752. Min Act: -0.1700

Data Index: 1363707 (Open Web Text)

Max Activating Token Index: 543

Text #16

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.8102. Min Act: -0.1700

Data Index: 6427010 (Open Web Text)

Max Activating Token Index: 121

Text #17

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.7925. Min Act: -0.1700

Data Index: 5015772 (Open Web Text)

Max Activating Token Index: 969

Text #18

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.7595. Min Act: -0.1700

Data Index: 1867879 (Open Web Text)

Max Activating Token Index: 160

Text #19

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.7637. Min Act: -0.1700

Data Index: 5171043 (Open Web Text)

Max Activating Token Index: 158