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

Dataset: Open Web Text

Neuron 2631 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: 1.6472. Min Range: -1.6472

Max Act: 1.6472. Min Act: -0.1687

Data Index: 5059205 (Open Web Text)

Max Activating Token Index: 11

Text #1

Max Range: 1.6472. Min Range: -1.6472

Max Act: 1.6377. Min Act: -0.1700

Data Index: 1138594 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 1.6472. Min Range: -1.6472

Max Act: 1.6214. Min Act: -0.1675

Data Index: 2494 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 1.6472. Min Range: -1.6472

Max Act: 1.6123. Min Act: -0.1697

Data Index: 4201330 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 1.6472. Min Range: -1.6472

Max Act: 1.5982. Min Act: -0.1691

Data Index: 331238 (Open Web Text)

Max Activating Token Index: 12

Text #5

Max Range: 1.6472. Min Range: -1.6472

Max Act: 1.5896. Min Act: -0.1698

Data Index: 2630710 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 1.6472. Min Range: -1.6472

Max Act: 1.5912. Min Act: -0.1697

Data Index: 1803079 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 1.6472. Min Range: -1.6472

Max Act: 1.5951. Min Act: -0.1700

Data Index: 4486631 (Open Web Text)

Max Activating Token Index: 11

Text #8

Max Range: 1.6472. Min Range: -1.6472

Max Act: 1.5762. Min Act: -0.1699

Data Index: 251302 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 1.6472. Min Range: -1.6472

Max Act: 1.5762. Min Act: -0.1700

Data Index: 5487765 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 1.6472. Min Range: -1.6472

Max Act: 1.5762. Min Act: -0.1700

Data Index: 2759291 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 1.6472. Min Range: -1.6472

Max Act: 1.5780. Min Act: -0.1700

Data Index: 7184148 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 1.6472. Min Range: -1.6472

Max Act: 1.5792. Min Act: -0.1670

Data Index: 2417919 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 1.6472. Min Range: -1.6472

Max Act: 1.5719. Min Act: -0.1678

Data Index: 7761757 (Open Web Text)

Max Activating Token Index: 14

Text #14

Max Range: 1.6472. Min Range: -1.6472

Max Act: 1.5661. Min Act: -0.1694

Data Index: 3153181 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 1.6472. Min Range: -1.6472

Max Act: 1.5691. Min Act: -0.1684

Data Index: 1146887 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 1.6472. Min Range: -1.6472

Max Act: 1.5623. Min Act: -0.1700

Data Index: 5042288 (Open Web Text)

Max Activating Token Index: 10

Text #17

Max Range: 1.6472. Min Range: -1.6472

Max Act: 1.5605. Min Act: -0.1694

Data Index: 3359014 (Open Web Text)

Max Activating Token Index: 864

Text #18

Max Range: 1.6472. Min Range: -1.6472

Max Act: 1.5558. Min Act: -0.1700

Data Index: 93832 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 1.6472. Min Range: -1.6472

Max Act: 1.5583. Min Act: -0.1700

Data Index: 8562147 (Open Web Text)

Max Activating Token Index: 12