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

Dataset: Open Web Text

Neuron 2452 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: 8.5992. Min Range: -8.5992

Max Act: 8.5992. Min Act: -0.1700

Data Index: 6892014 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 8.5992. Min Range: -8.5992

Max Act: 7.9232. Min Act: -0.1700

Data Index: 1151345 (Open Web Text)

Max Activating Token Index: 968

Text #2

Max Range: 8.5992. Min Range: -8.5992

Max Act: 7.8510. Min Act: -0.1690

Data Index: 104652 (Open Web Text)

Max Activating Token Index: 534

Text #3

Max Range: 8.5992. Min Range: -8.5992

Max Act: 7.8741. Min Act: -0.1671

Data Index: 8321150 (Open Web Text)

Max Activating Token Index: 232

Text #4

Max Range: 8.5992. Min Range: -8.5992

Max Act: 7.8702. Min Act: -0.1620

Data Index: 3950734 (Open Web Text)

Max Activating Token Index: 856

Text #5

Max Range: 8.5992. Min Range: -8.5992

Max Act: 7.7566. Min Act: -0.1692

Data Index: 4506428 (Open Web Text)

Max Activating Token Index: 56

Text #6

Max Range: 8.5992. Min Range: -8.5992

Max Act: 7.8012. Min Act: -0.1668

Data Index: 1550771 (Open Web Text)

Max Activating Token Index: 387

Text #7

Max Range: 8.5992. Min Range: -8.5992

Max Act: 7.7999. Min Act: -0.1661

Data Index: 6989676 (Open Web Text)

Max Activating Token Index: 273

Text #8

Max Range: 8.5992. Min Range: -8.5992

Max Act: 7.6312. Min Act: -0.1694

Data Index: 8727789 (Open Web Text)

Max Activating Token Index: 838

Text #9

Max Range: 8.5992. Min Range: -8.5992

Max Act: 7.6503. Min Act: -0.1700

Data Index: 6927131 (Open Web Text)

Max Activating Token Index: 772

Text #10

Max Range: 8.5992. Min Range: -8.5992

Max Act: 7.5913. Min Act: -0.1700

Data Index: 1772667 (Open Web Text)

Max Activating Token Index: 930

Text #11

Max Range: 8.5992. Min Range: -8.5992

Max Act: 7.6029. Min Act: -0.1700

Data Index: 7931195 (Open Web Text)

Max Activating Token Index: 947

Text #12

Max Range: 8.5992. Min Range: -8.5992

Max Act: 7.5895. Min Act: -0.1700

Data Index: 953223 (Open Web Text)

Max Activating Token Index: 37

Text #13

Max Range: 8.5992. Min Range: -8.5992

Max Act: 7.5652. Min Act: -0.1699

Data Index: 7782865 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 8.5992. Min Range: -8.5992

Max Act: 7.6020. Min Act: -0.1700

Data Index: 6741494 (Open Web Text)

Max Activating Token Index: 757

Text #15

Max Range: 8.5992. Min Range: -8.5992

Max Act: 7.5770. Min Act: -0.1700

Data Index: 1008217 (Open Web Text)

Max Activating Token Index: 461

Text #16

Max Range: 8.5992. Min Range: -8.5992

Max Act: 7.6366. Min Act: -0.1697

Data Index: 2696455 (Open Web Text)

Max Activating Token Index: 934

Text #17

Max Range: 8.5992. Min Range: -8.5992

Max Act: 7.6138. Min Act: -0.1625

Data Index: 8369426 (Open Web Text)

Max Activating Token Index: 901

Text #18

Max Range: 8.5992. Min Range: -8.5992

Max Act: 7.5128. Min Act: -0.1695

Data Index: 4469290 (Open Web Text)

Max Activating Token Index: 165

Text #19

Max Range: 8.5992. Min Range: -8.5992

Max Act: 7.5748. Min Act: -0.1678

Data Index: 6069397 (Open Web Text)

Max Activating Token Index: 781