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

Dataset: Open Web Text

Neuron 1263 in Layer 6

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: 3.2928. Min Range: -3.2928

Max Act: 3.2928. Min Act: -0.1700

Data Index: 6581487 (Open Web Text)

Max Activating Token Index: 410

Text #1

Max Range: 3.2928. Min Range: -3.2928

Max Act: 3.2056. Min Act: -0.1700

Data Index: 4222643 (Open Web Text)

Max Activating Token Index: 826

Text #2

Max Range: 3.2928. Min Range: -3.2928

Max Act: 3.1928. Min Act: -0.1700

Data Index: 7523677 (Open Web Text)

Max Activating Token Index: 421

Text #3

Max Range: 3.2928. Min Range: -3.2928

Max Act: 3.1505. Min Act: -0.1700

Data Index: 3799853 (Open Web Text)

Max Activating Token Index: 514

Text #4

Max Range: 3.2928. Min Range: -3.2928

Max Act: 3.1692. Min Act: -0.1700

Data Index: 1668812 (Open Web Text)

Max Activating Token Index: 607

Text #5

Max Range: 3.2928. Min Range: -3.2928

Max Act: 3.1584. Min Act: -0.1700

Data Index: 4949411 (Open Web Text)

Max Activating Token Index: 783

Text #6

Max Range: 3.2928. Min Range: -3.2928

Max Act: 3.1645. Min Act: -0.1700

Data Index: 2058616 (Open Web Text)

Max Activating Token Index: 303

Text #7

Max Range: 3.2928. Min Range: -3.2928

Max Act: 3.1287. Min Act: -0.1700

Data Index: 8013027 (Open Web Text)

Max Activating Token Index: 1002

Text #8

Max Range: 3.2928. Min Range: -3.2928

Max Act: 3.1325. Min Act: -0.1700

Data Index: 2249309 (Open Web Text)

Max Activating Token Index: 875

Text #9

Max Range: 3.2928. Min Range: -3.2928

Max Act: 3.1224. Min Act: -0.1700

Data Index: 1225552 (Open Web Text)

Max Activating Token Index: 902

Text #10

Max Range: 3.2928. Min Range: -3.2928

Max Act: 3.1196. Min Act: -0.1700

Data Index: 2177685 (Open Web Text)

Max Activating Token Index: 200

Text #11

Max Range: 3.2928. Min Range: -3.2928

Max Act: 3.1179. Min Act: -0.1700

Data Index: 2701588 (Open Web Text)

Max Activating Token Index: 796

Text #12

Max Range: 3.2928. Min Range: -3.2928

Max Act: 3.1252. Min Act: -0.1700

Data Index: 5529927 (Open Web Text)

Max Activating Token Index: 610

Text #13

Max Range: 3.2928. Min Range: -3.2928

Max Act: 3.1275. Min Act: -0.1700

Data Index: 8710822 (Open Web Text)

Max Activating Token Index: 582

Text #14

Max Range: 3.2928. Min Range: -3.2928

Max Act: 3.0984. Min Act: -0.1700

Data Index: 1161706 (Open Web Text)

Max Activating Token Index: 695

Text #15

Max Range: 3.2928. Min Range: -3.2928

Max Act: 3.1231. Min Act: -0.1700

Data Index: 108767 (Open Web Text)

Max Activating Token Index: 469

Text #16

Max Range: 3.2928. Min Range: -3.2928

Max Act: 3.1092. Min Act: -0.1700

Data Index: 3152703 (Open Web Text)

Max Activating Token Index: 874

Text #17

Max Range: 3.2928. Min Range: -3.2928

Max Act: 3.0775. Min Act: -0.1700

Data Index: 2036741 (Open Web Text)

Max Activating Token Index: 890

Text #18

Max Range: 3.2928. Min Range: -3.2928

Max Act: 3.0628. Min Act: -0.1700

Data Index: 5274487 (Open Web Text)

Max Activating Token Index: 868

Text #19

Max Range: 3.2928. Min Range: -3.2928

Max Act: 3.0853. Min Act: -0.1700

Data Index: 6653881 (Open Web Text)

Max Activating Token Index: 359