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

Dataset: Open Web Text

Neuron 627 in Layer 2

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: 1.1692. Min Range: -1.1692

Max Act: 1.1692. Min Act: -0.1700

Data Index: 7557671 (Open Web Text)

Max Activating Token Index: 714

Text #1

Max Range: 1.1692. Min Range: -1.1692

Max Act: 1.1657. Min Act: -0.1699

Data Index: 157864 (Open Web Text)

Max Activating Token Index: 225

Text #2

Max Range: 1.1692. Min Range: -1.1692

Max Act: 1.1426. Min Act: -0.1699

Data Index: 1775699 (Open Web Text)

Max Activating Token Index: 900

Text #3

Max Range: 1.1692. Min Range: -1.1692

Max Act: 1.1517. Min Act: -0.1700

Data Index: 411094 (Open Web Text)

Max Activating Token Index: 838

Text #4

Max Range: 1.1692. Min Range: -1.1692

Max Act: 1.1503. Min Act: -0.1700

Data Index: 6755020 (Open Web Text)

Max Activating Token Index: 551

Text #5

Max Range: 1.1692. Min Range: -1.1692

Max Act: 1.1411. Min Act: -0.1699

Data Index: 1732772 (Open Web Text)

Max Activating Token Index: 987

Text #6

Max Range: 1.1692. Min Range: -1.1692

Max Act: 1.1477. Min Act: -0.1692

Data Index: 1719236 (Open Web Text)

Max Activating Token Index: 798

Text #7

Max Range: 1.1692. Min Range: -1.1692

Max Act: 1.1402. Min Act: -0.1696

Data Index: 79113 (Open Web Text)

Max Activating Token Index: 704

Text #8

Max Range: 1.1692. Min Range: -1.1692

Max Act: 1.1275. Min Act: -0.1700

Data Index: 5738017 (Open Web Text)

Max Activating Token Index: 208

Text #9

Max Range: 1.1692. Min Range: -1.1692

Max Act: 1.1333. Min Act: -0.1700

Data Index: 6343994 (Open Web Text)

Max Activating Token Index: 412

Text #10

Max Range: 1.1692. Min Range: -1.1692

Max Act: 1.1187. Min Act: -0.1693

Data Index: 1595425 (Open Web Text)

Max Activating Token Index: 489

Text #11

Max Range: 1.1692. Min Range: -1.1692

Max Act: 1.1198. Min Act: -0.1700

Data Index: 51281 (Open Web Text)

Max Activating Token Index: 94

Text #12

Max Range: 1.1692. Min Range: -1.1692

Max Act: 1.1042. Min Act: -0.1700

Data Index: 4235703 (Open Web Text)

Max Activating Token Index: 381

Text #13

Max Range: 1.1692. Min Range: -1.1692

Max Act: 1.1071. Min Act: -0.1699

Data Index: 8420251 (Open Web Text)

Max Activating Token Index: 510

Text #14

Max Range: 1.1692. Min Range: -1.1692

Max Act: 1.1071. Min Act: -0.1700

Data Index: 6242646 (Open Web Text)

Max Activating Token Index: 550

Text #15

Max Range: 1.1692. Min Range: -1.1692

Max Act: 1.1026. Min Act: -0.1700

Data Index: 744831 (Open Web Text)

Max Activating Token Index: 907

Text #16

Max Range: 1.1692. Min Range: -1.1692

Max Act: 1.0926. Min Act: -0.1700

Data Index: 1240562 (Open Web Text)

Max Activating Token Index: 11

Text #17

Max Range: 1.1692. Min Range: -1.1692

Max Act: 1.1069. Min Act: -0.1700

Data Index: 5465757 (Open Web Text)

Max Activating Token Index: 954

Text #18

Max Range: 1.1692. Min Range: -1.1692

Max Act: 1.0974. Min Act: -0.1700

Data Index: 230103 (Open Web Text)

Max Activating Token Index: 10

Text #19

Max Range: 1.1692. Min Range: -1.1692

Max Act: 1.1029. Min Act: -0.1698

Data Index: 4798280 (Open Web Text)

Max Activating Token Index: 401