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

Dataset: Open Web Text

Neuron 2260 in Layer 1

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: 1.7721. Min Range: -1.7721

Max Act: 1.7721. Min Act: -0.1700

Data Index: 5983624 (Open Web Text)

Max Activating Token Index: 372

Text #1

Max Range: 1.7721. Min Range: -1.7721

Max Act: 1.7610. Min Act: -0.1700

Data Index: 6673888 (Open Web Text)

Max Activating Token Index: 50

Text #2

Max Range: 1.7721. Min Range: -1.7721

Max Act: 1.7432. Min Act: -0.1699

Data Index: 4647933 (Open Web Text)

Max Activating Token Index: 50

Text #3

Max Range: 1.7721. Min Range: -1.7721

Max Act: 1.7257. Min Act: -0.1700

Data Index: 3936111 (Open Web Text)

Max Activating Token Index: 962

Text #4

Max Range: 1.7721. Min Range: -1.7721

Max Act: 1.7176. Min Act: -0.1700

Data Index: 8403413 (Open Web Text)

Max Activating Token Index: 985

Text #5

Max Range: 1.7721. Min Range: -1.7721

Max Act: 1.7184. Min Act: -0.1700

Data Index: 3742236 (Open Web Text)

Max Activating Token Index: 69

Text #6

Max Range: 1.7721. Min Range: -1.7721

Max Act: 1.7105. Min Act: -0.1700

Data Index: 72031 (Open Web Text)

Max Activating Token Index: 42

Text #7

Max Range: 1.7721. Min Range: -1.7721

Max Act: 1.7116. Min Act: -0.1700

Data Index: 7614182 (Open Web Text)

Max Activating Token Index: 709

Text #8

Max Range: 1.7721. Min Range: -1.7721

Max Act: 1.7034. Min Act: -0.1700

Data Index: 5169368 (Open Web Text)

Max Activating Token Index: 105

Text #9

Max Range: 1.7721. Min Range: -1.7721

Max Act: 1.7067. Min Act: -0.1700

Data Index: 2630571 (Open Web Text)

Max Activating Token Index: 631

Text #10

Max Range: 1.7721. Min Range: -1.7721

Max Act: 1.6987. Min Act: -0.1700

Data Index: 5956810 (Open Web Text)

Max Activating Token Index: 636

Text #11

Max Range: 1.7721. Min Range: -1.7721

Max Act: 1.7066. Min Act: -0.1700

Data Index: 2921599 (Open Web Text)

Max Activating Token Index: 388

Text #12

Max Range: 1.7721. Min Range: -1.7721

Max Act: 1.6951. Min Act: -0.1700

Data Index: 5190468 (Open Web Text)

Max Activating Token Index: 28

Text #13

Max Range: 1.7721. Min Range: -1.7721

Max Act: 1.6909. Min Act: -0.1700

Data Index: 628207 (Open Web Text)

Max Activating Token Index: 1016

Text #14

Max Range: 1.7721. Min Range: -1.7721

Max Act: 1.6796. Min Act: -0.1700

Data Index: 7642731 (Open Web Text)

Max Activating Token Index: 79

Text #15

Max Range: 1.7721. Min Range: -1.7721

Max Act: 1.6826. Min Act: -0.1700

Data Index: 2092440 (Open Web Text)

Max Activating Token Index: 133

Text #16

Max Range: 1.7721. Min Range: -1.7721

Max Act: 1.6776. Min Act: -0.1700

Data Index: 1787717 (Open Web Text)

Max Activating Token Index: 422

Text #17

Max Range: 1.7721. Min Range: -1.7721

Max Act: 1.6810. Min Act: -0.1700

Data Index: 2196889 (Open Web Text)

Max Activating Token Index: 131

Text #18

Max Range: 1.7721. Min Range: -1.7721

Max Act: 1.6710. Min Act: -0.1700

Data Index: 1716581 (Open Web Text)

Max Activating Token Index: 968

Text #19

Max Range: 1.7721. Min Range: -1.7721

Max Act: 1.6790. Min Act: -0.1700

Data Index: 2157526 (Open Web Text)

Max Activating Token Index: 233