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

Dataset: Open Web Text

Neuron 1702 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: 3.2632. Min Range: -3.2632

Max Act: 3.2632. Min Act: -0.1700

Data Index: 2800918 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.1848. Min Act: -0.1700

Data Index: 8712940 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.1838. Min Act: -0.1700

Data Index: 6818853 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.1715. Min Act: -0.1700

Data Index: 4990009 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.1350. Min Act: -0.1700

Data Index: 420312 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.1385. Min Act: -0.1700

Data Index: 7099300 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.1158. Min Act: -0.1700

Data Index: 7015099 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.0855. Min Act: -0.1700

Data Index: 3427470 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.0863. Min Act: -0.1700

Data Index: 3685277 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.0761. Min Act: -0.1700

Data Index: 1160642 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.0681. Min Act: -0.1700

Data Index: 6842118 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.0726. Min Act: -0.1700

Data Index: 6826274 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.0646. Min Act: -0.1700

Data Index: 4713145 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.0693. Min Act: -0.1700

Data Index: 1383874 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.0710. Min Act: -0.1700

Data Index: 4163552 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.0642. Min Act: -0.1700

Data Index: 6552177 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.0712. Min Act: -0.1700

Data Index: 1271070 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.0834. Min Act: -0.1700

Data Index: 3466787 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.0817. Min Act: -0.1700

Data Index: 6493884 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.0725. Min Act: -0.1700

Data Index: 1722661 (Open Web Text)

Max Activating Token Index: 8