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

Dataset: Open Web Text

Neuron 1852 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: 2.1643. Min Range: -2.1643

Max Act: 2.1643. Min Act: -0.1700

Data Index: 6257513 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 2.1643. Min Range: -2.1643

Max Act: 2.1124. Min Act: -0.1700

Data Index: 1130731 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 2.1643. Min Range: -2.1643

Max Act: 2.1124. Min Act: -0.1700

Data Index: 7200607 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 2.1643. Min Range: -2.1643

Max Act: 2.1124. Min Act: -0.1700

Data Index: 4868593 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 2.1643. Min Range: -2.1643

Max Act: 2.1124. Min Act: -0.1700

Data Index: 1460577 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 2.1643. Min Range: -2.1643

Max Act: 2.1124. Min Act: -0.1700

Data Index: 3081841 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 2.1643. Min Range: -2.1643

Max Act: 2.0944. Min Act: -0.1700

Data Index: 3544520 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 2.1643. Min Range: -2.1643

Max Act: 2.0909. Min Act: -0.1700

Data Index: 8760938 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 2.1643. Min Range: -2.1643

Max Act: 2.0994. Min Act: -0.1700

Data Index: 4319108 (Open Web Text)

Max Activating Token Index: 16

Text #9

Max Range: 2.1643. Min Range: -2.1643

Max Act: 2.0894. Min Act: -0.1700

Data Index: 4232969 (Open Web Text)

Max Activating Token Index: 13

Text #10

Max Range: 2.1643. Min Range: -2.1643

Max Act: 2.0825. Min Act: -0.1700

Data Index: 4580505 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 2.1643. Min Range: -2.1643

Max Act: 2.0756. Min Act: -0.1700

Data Index: 3178510 (Open Web Text)

Max Activating Token Index: 15

Text #12

Max Range: 2.1643. Min Range: -2.1643

Max Act: 2.0802. Min Act: -0.1700

Data Index: 7070967 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 2.1643. Min Range: -2.1643

Max Act: 2.0742. Min Act: -0.1700

Data Index: 604120 (Open Web Text)

Max Activating Token Index: 16

Text #14

Max Range: 2.1643. Min Range: -2.1643

Max Act: 2.0763. Min Act: -0.1700

Data Index: 2976294 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 2.1643. Min Range: -2.1643

Max Act: 2.0736. Min Act: -0.1700

Data Index: 2959880 (Open Web Text)

Max Activating Token Index: 11

Text #16

Max Range: 2.1643. Min Range: -2.1643

Max Act: 2.0841. Min Act: -0.1700

Data Index: 2761916 (Open Web Text)

Max Activating Token Index: 12

Text #17

Max Range: 2.1643. Min Range: -2.1643

Max Act: 2.0734. Min Act: -0.1700

Data Index: 4609380 (Open Web Text)

Max Activating Token Index: 9

Text #18

Max Range: 2.1643. Min Range: -2.1643

Max Act: 2.0858. Min Act: -0.1700

Data Index: 3995634 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 2.1643. Min Range: -2.1643

Max Act: 2.0813. Min Act: -0.1700

Data Index: 5407218 (Open Web Text)

Max Activating Token Index: 7