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

Dataset: Open Web Text

Neuron 896 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: 5.4653. Min Range: -5.4653

Max Act: 5.4653. Min Act: -0.1700

Data Index: 5894487 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 5.4653. Min Range: -5.4653

Max Act: 5.4623. Min Act: -0.1700

Data Index: 7724360 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 5.4653. Min Range: -5.4653

Max Act: 5.4540. Min Act: -0.1700

Data Index: 6144742 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 5.4653. Min Range: -5.4653

Max Act: 5.3911. Min Act: -0.1700

Data Index: 5945849 (Open Web Text)

Max Activating Token Index: 10

Text #4

Max Range: 5.4653. Min Range: -5.4653

Max Act: 5.4156. Min Act: -0.1700

Data Index: 5614160 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 5.4653. Min Range: -5.4653

Max Act: 5.3747. Min Act: -0.1700

Data Index: 8223565 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 5.4653. Min Range: -5.4653

Max Act: 5.3696. Min Act: -0.1700

Data Index: 797574 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 5.4653. Min Range: -5.4653

Max Act: 5.3806. Min Act: -0.1700

Data Index: 4028861 (Open Web Text)

Max Activating Token Index: 12

Text #8

Max Range: 5.4653. Min Range: -5.4653

Max Act: 5.3873. Min Act: -0.1700

Data Index: 788991 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 5.4653. Min Range: -5.4653

Max Act: 5.3455. Min Act: -0.1700

Data Index: 2622553 (Open Web Text)

Max Activating Token Index: 18

Text #10

Max Range: 5.4653. Min Range: -5.4653

Max Act: 5.3303. Min Act: -0.1700

Data Index: 1606497 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 5.4653. Min Range: -5.4653

Max Act: 5.3396. Min Act: -0.1700

Data Index: 1727080 (Open Web Text)

Max Activating Token Index: 11

Text #12

Max Range: 5.4653. Min Range: -5.4653

Max Act: 5.3432. Min Act: -0.1700

Data Index: 2274156 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 5.4653. Min Range: -5.4653

Max Act: 5.3556. Min Act: -0.1700

Data Index: 6673152 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 5.4653. Min Range: -5.4653

Max Act: 5.2915. Min Act: -0.1700

Data Index: 2028735 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 5.4653. Min Range: -5.4653

Max Act: 5.3212. Min Act: -0.1700

Data Index: 5840122 (Open Web Text)

Max Activating Token Index: 20

Text #16

Max Range: 5.4653. Min Range: -5.4653

Max Act: 5.2988. Min Act: -0.1700

Data Index: 6862327 (Open Web Text)

Max Activating Token Index: 22

Text #17

Max Range: 5.4653. Min Range: -5.4653

Max Act: 5.3073. Min Act: -0.1700

Data Index: 5566841 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 5.4653. Min Range: -5.4653

Max Act: 5.3178. Min Act: -0.1700

Data Index: 2246581 (Open Web Text)

Max Activating Token Index: 11

Text #19

Max Range: 5.4653. Min Range: -5.4653

Max Act: 5.3151. Min Act: -0.1700

Data Index: 4226766 (Open Web Text)

Max Activating Token Index: 7