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

Dataset: Open Web Text

Neuron 822 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: 2.1811. Min Range: -2.1811

Max Act: 2.1811. Min Act: -0.1693

Data Index: 4150052 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 2.1811. Min Range: -2.1811

Max Act: 2.1571. Min Act: -0.1700

Data Index: 4512913 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 2.1811. Min Range: -2.1811

Max Act: 2.1518. Min Act: -0.1699

Data Index: 8131237 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 2.1811. Min Range: -2.1811

Max Act: 2.1382. Min Act: -0.1700

Data Index: 809080 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 2.1811. Min Range: -2.1811

Max Act: 2.1370. Min Act: -0.1700

Data Index: 2592760 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 2.1811. Min Range: -2.1811

Max Act: 2.1027. Min Act: -0.1685

Data Index: 7268470 (Open Web Text)

Max Activating Token Index: 234

Text #6

Max Range: 2.1811. Min Range: -2.1811

Max Act: 2.1163. Min Act: -0.1700

Data Index: 4012090 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 2.1811. Min Range: -2.1811

Max Act: 2.1095. Min Act: -0.1700

Data Index: 138458 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 2.1811. Min Range: -2.1811

Max Act: 2.1075. Min Act: -0.1680

Data Index: 2181745 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 2.1811. Min Range: -2.1811

Max Act: 2.1148. Min Act: -0.1700

Data Index: 1297183 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 2.1811. Min Range: -2.1811

Max Act: 2.0965. Min Act: -0.1688

Data Index: 6411315 (Open Web Text)

Max Activating Token Index: 10

Text #11

Max Range: 2.1811. Min Range: -2.1811

Max Act: 2.0946. Min Act: -0.1696

Data Index: 737004 (Open Web Text)

Max Activating Token Index: 945

Text #12

Max Range: 2.1811. Min Range: -2.1811

Max Act: 2.0862. Min Act: -0.1699

Data Index: 3133352 (Open Web Text)

Max Activating Token Index: 922

Text #13

Max Range: 2.1811. Min Range: -2.1811

Max Act: 2.0888. Min Act: -0.1700

Data Index: 3416053 (Open Web Text)

Max Activating Token Index: 949

Text #14

Max Range: 2.1811. Min Range: -2.1811

Max Act: 2.0945. Min Act: -0.1700

Data Index: 1401582 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 2.1811. Min Range: -2.1811

Max Act: 2.0996. Min Act: -0.1699

Data Index: 2023126 (Open Web Text)

Max Activating Token Index: 10

Text #16

Max Range: 2.1811. Min Range: -2.1811

Max Act: 2.0921. Min Act: -0.1700

Data Index: 398798 (Open Web Text)

Max Activating Token Index: 12

Text #17

Max Range: 2.1811. Min Range: -2.1811

Max Act: 2.0922. Min Act: -0.1696

Data Index: 2081399 (Open Web Text)

Max Activating Token Index: 914

Text #18

Max Range: 2.1811. Min Range: -2.1811

Max Act: 2.0709. Min Act: -0.1699

Data Index: 3768316 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 2.1811. Min Range: -2.1811

Max Act: 2.0721. Min Act: -0.1681

Data Index: 1640836 (Open Web Text)

Max Activating Token Index: 33