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

Dataset: Open Web Text

Neuron 2450 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: 5.4602. Min Range: -5.4602

Max Act: 5.4602. Min Act: -0.1666

Data Index: 1723385 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 5.4602. Min Range: -5.4602

Max Act: 5.1999. Min Act: -0.1679

Data Index: 3133170 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 5.4602. Min Range: -5.4602

Max Act: 5.1700. Min Act: -0.1698

Data Index: 3234306 (Open Web Text)

Max Activating Token Index: 179

Text #3

Max Range: 5.4602. Min Range: -5.4602

Max Act: 5.1053. Min Act: -0.1469

Data Index: 7706782 (Open Web Text)

Max Activating Token Index: 27

Text #4

Max Range: 5.4602. Min Range: -5.4602

Max Act: 5.0901. Min Act: -0.1692

Data Index: 4892230 (Open Web Text)

Max Activating Token Index: 9

Text #5

Max Range: 5.4602. Min Range: -5.4602

Max Act: 5.0978. Min Act: -0.1688

Data Index: 8652028 (Open Web Text)

Max Activating Token Index: 13

Text #6

Max Range: 5.4602. Min Range: -5.4602

Max Act: 5.1107. Min Act: -0.1700

Data Index: 3255883 (Open Web Text)

Max Activating Token Index: 81

Text #7

Max Range: 5.4602. Min Range: -5.4602

Max Act: 5.1204. Min Act: -0.1676

Data Index: 1110123 (Open Web Text)

Max Activating Token Index: 175

Text #8

Max Range: 5.4602. Min Range: -5.4602

Max Act: 5.0879. Min Act: -0.1689

Data Index: 8287808 (Open Web Text)

Max Activating Token Index: 47

Text #9

Max Range: 5.4602. Min Range: -5.4602

Max Act: 5.0730. Min Act: -0.1586

Data Index: 8522196 (Open Web Text)

Max Activating Token Index: 35

Text #10

Max Range: 5.4602. Min Range: -5.4602

Max Act: 5.0706. Min Act: -0.1653

Data Index: 1640147 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 5.4602. Min Range: -5.4602

Max Act: 5.0832. Min Act: -0.1691

Data Index: 7051956 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 5.4602. Min Range: -5.4602

Max Act: 5.0854. Min Act: -0.1681

Data Index: 2914906 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 5.4602. Min Range: -5.4602

Max Act: 5.0654. Min Act: -0.1584

Data Index: 430555 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 5.4602. Min Range: -5.4602

Max Act: 5.0904. Min Act: -0.1607

Data Index: 5763815 (Open Web Text)

Max Activating Token Index: 193

Text #15

Max Range: 5.4602. Min Range: -5.4602

Max Act: 5.0725. Min Act: -0.1489

Data Index: 2959118 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 5.4602. Min Range: -5.4602

Max Act: 5.0589. Min Act: -0.1693

Data Index: 2785486 (Open Web Text)

Max Activating Token Index: 291

Text #17

Max Range: 5.4602. Min Range: -5.4602

Max Act: 5.0255. Min Act: -0.1700

Data Index: 1343584 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 5.4602. Min Range: -5.4602

Max Act: 5.0432. Min Act: -0.1680

Data Index: 1533804 (Open Web Text)

Max Activating Token Index: 63

Text #19

Max Range: 5.4602. Min Range: -5.4602

Max Act: 5.0308. Min Act: -0.1684

Data Index: 873178 (Open Web Text)

Max Activating Token Index: 6