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

Dataset: Open Web Text

Neuron 792 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: 4.9045. Min Range: -4.9045

Max Act: 4.9045. Min Act: -0.1700

Data Index: 6925694 (Open Web Text)

Max Activating Token Index: 507

Text #1

Max Range: 4.9045. Min Range: -4.9045

Max Act: 4.8311. Min Act: -0.1700

Data Index: 2921720 (Open Web Text)

Max Activating Token Index: 666

Text #2

Max Range: 4.9045. Min Range: -4.9045

Max Act: 4.8201. Min Act: -0.1700

Data Index: 306609 (Open Web Text)

Max Activating Token Index: 417

Text #3

Max Range: 4.9045. Min Range: -4.9045

Max Act: 4.7662. Min Act: -0.1700

Data Index: 7138146 (Open Web Text)

Max Activating Token Index: 979

Text #4

Max Range: 4.9045. Min Range: -4.9045

Max Act: 4.7881. Min Act: -0.1700

Data Index: 772488 (Open Web Text)

Max Activating Token Index: 536

Text #5

Max Range: 4.9045. Min Range: -4.9045

Max Act: 4.6752. Min Act: -0.1700

Data Index: 3289977 (Open Web Text)

Max Activating Token Index: 344

Text #6

Max Range: 4.9045. Min Range: -4.9045

Max Act: 4.6838. Min Act: -0.1700

Data Index: 69133 (Open Web Text)

Max Activating Token Index: 666

Text #7

Max Range: 4.9045. Min Range: -4.9045

Max Act: 4.6174. Min Act: -0.1700

Data Index: 5313275 (Open Web Text)

Max Activating Token Index: 922

Text #8

Max Range: 4.9045. Min Range: -4.9045

Max Act: 4.6675. Min Act: -0.1700

Data Index: 1819180 (Open Web Text)

Max Activating Token Index: 68

Text #9

Max Range: 4.9045. Min Range: -4.9045

Max Act: 4.6029. Min Act: -0.1700

Data Index: 2702421 (Open Web Text)

Max Activating Token Index: 127

Text #10

Max Range: 4.9045. Min Range: -4.9045

Max Act: 4.5927. Min Act: -0.1700

Data Index: 2949230 (Open Web Text)

Max Activating Token Index: 406

Text #11

Max Range: 4.9045. Min Range: -4.9045

Max Act: 4.5969. Min Act: -0.1700

Data Index: 5299753 (Open Web Text)

Max Activating Token Index: 314

Text #12

Max Range: 4.9045. Min Range: -4.9045

Max Act: 4.5985. Min Act: -0.1700

Data Index: 4624182 (Open Web Text)

Max Activating Token Index: 68

Text #13

Max Range: 4.9045. Min Range: -4.9045

Max Act: 4.5518. Min Act: -0.1700

Data Index: 7244060 (Open Web Text)

Max Activating Token Index: 304

Text #14

Max Range: 4.9045. Min Range: -4.9045

Max Act: 4.5405. Min Act: -0.1700

Data Index: 2449985 (Open Web Text)

Max Activating Token Index: 814

Text #15

Max Range: 4.9045. Min Range: -4.9045

Max Act: 4.5719. Min Act: -0.1700

Data Index: 1604916 (Open Web Text)

Max Activating Token Index: 522

Text #16

Max Range: 4.9045. Min Range: -4.9045

Max Act: 4.5294. Min Act: -0.1700

Data Index: 3792095 (Open Web Text)

Max Activating Token Index: 857

Text #17

Max Range: 4.9045. Min Range: -4.9045

Max Act: 4.4835. Min Act: -0.1700

Data Index: 2159677 (Open Web Text)

Max Activating Token Index: 551

Text #18

Max Range: 4.9045. Min Range: -4.9045

Max Act: 4.5045. Min Act: -0.1700

Data Index: 253357 (Open Web Text)

Max Activating Token Index: 602

Text #19

Max Range: 4.9045. Min Range: -4.9045

Max Act: 4.4897. Min Act: -0.1700

Data Index: 5180041 (Open Web Text)

Max Activating Token Index: 1010