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

Dataset: Open Web Text

Neuron 2703 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: 1.1079. Min Range: -1.1079

Max Act: 1.1079. Min Act: -0.1700

Data Index: 1433873 (Open Web Text)

Max Activating Token Index: 20

Text #1

Max Range: 1.1079. Min Range: -1.1079

Max Act: 1.0890. Min Act: -0.1697

Data Index: 2376103 (Open Web Text)

Max Activating Token Index: 10

Text #2

Max Range: 1.1079. Min Range: -1.1079

Max Act: 1.0618. Min Act: -0.1678

Data Index: 2117700 (Open Web Text)

Max Activating Token Index: 20

Text #3

Max Range: 1.1079. Min Range: -1.1079

Max Act: 1.0635. Min Act: -0.1485

Data Index: 766309 (Open Web Text)

Max Activating Token Index: 13

Text #4

Max Range: 1.1079. Min Range: -1.1079

Max Act: 1.0295. Min Act: -0.1700

Data Index: 21 (Open Web Text)

Max Activating Token Index: 0

Text #5

Max Range: 1.1079. Min Range: -1.1079

Max Act: 1.0295. Min Act: -0.1463

Data Index: 20 (Open Web Text)

Max Activating Token Index: 0

Text #6

Max Range: 1.1079. Min Range: -1.1079

Max Act: 1.0295. Min Act: -0.1495

Data Index: 22 (Open Web Text)

Max Activating Token Index: 0

Text #7

Max Range: 1.1079. Min Range: -1.1079

Max Act: 1.0295. Min Act: -0.1607

Data Index: 23 (Open Web Text)

Max Activating Token Index: 0

Text #8

Max Range: 1.1079. Min Range: -1.1079

Max Act: 1.0295. Min Act: -0.1688

Data Index: 11 (Open Web Text)

Max Activating Token Index: 0

Text #9

Max Range: 1.1079. Min Range: -1.1079

Max Act: 1.0295. Min Act: -0.1693

Data Index: 10 (Open Web Text)

Max Activating Token Index: 0

Text #10

Max Range: 1.1079. Min Range: -1.1079

Max Act: 1.0295. Min Act: -0.1692

Data Index: 8 (Open Web Text)

Max Activating Token Index: 0

Text #11

Max Range: 1.1079. Min Range: -1.1079

Max Act: 1.0295. Min Act: -0.1690

Data Index: 9 (Open Web Text)

Max Activating Token Index: 0

Text #12

Max Range: 1.1079. Min Range: -1.1079

Max Act: 1.0295. Min Act: -0.1699

Data Index: 13 (Open Web Text)

Max Activating Token Index: 0

Text #13

Max Range: 1.1079. Min Range: -1.1079

Max Act: 1.0295. Min Act: -0.1698

Data Index: 12 (Open Web Text)

Max Activating Token Index: 0

Text #14

Max Range: 1.1079. Min Range: -1.1079

Max Act: 1.0295. Min Act: -0.1635

Data Index: 14 (Open Web Text)

Max Activating Token Index: 0

Text #15

Max Range: 1.1079. Min Range: -1.1079

Max Act: 1.0295. Min Act: -0.1656

Data Index: 15 (Open Web Text)

Max Activating Token Index: 0

Text #16

Max Range: 1.1079. Min Range: -1.1079

Max Act: 1.0295. Min Act: -0.1662

Data Index: 3 (Open Web Text)

Max Activating Token Index: 0

Text #17

Max Range: 1.1079. Min Range: -1.1079

Max Act: 1.0295. Min Act: -0.1698

Data Index: 2 (Open Web Text)

Max Activating Token Index: 0

Text #18

Max Range: 1.1079. Min Range: -1.1079

Max Act: 1.0295. Min Act: -0.1674

Data Index: 0 (Open Web Text)

Max Activating Token Index: 0

Text #19

Max Range: 1.1079. Min Range: -1.1079

Max Act: 1.0295. Min Act: -0.1694

Data Index: 1 (Open Web Text)

Max Activating Token Index: 0