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

Dataset: Open Web Text

Neuron 1232 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: 4.3916. Min Range: -4.3916

Max Act: 4.3856. Min Act: -0.1700

Data Index: 7407401 (Open Web Text)

Max Activating Token Index: 712

Text #1

Max Range: 4.3916. Min Range: -4.3916

Max Act: 4.3916. Min Act: -0.1700

Data Index: 4956729 (Open Web Text)

Max Activating Token Index: 544

Text #2

Max Range: 4.3916. Min Range: -4.3916

Max Act: 4.3661. Min Act: -0.1700

Data Index: 977916 (Open Web Text)

Max Activating Token Index: 629

Text #3

Max Range: 4.3916. Min Range: -4.3916

Max Act: 4.3597. Min Act: -0.1700

Data Index: 3845190 (Open Web Text)

Max Activating Token Index: 573

Text #4

Max Range: 4.3916. Min Range: -4.3916

Max Act: 4.3407. Min Act: -0.1700

Data Index: 5756703 (Open Web Text)

Max Activating Token Index: 906

Text #5

Max Range: 4.3916. Min Range: -4.3916

Max Act: 4.1507. Min Act: -0.1700

Data Index: 2561789 (Open Web Text)

Max Activating Token Index: 676

Text #6

Max Range: 4.3916. Min Range: -4.3916

Max Act: 4.2213. Min Act: -0.1700

Data Index: 2659766 (Open Web Text)

Max Activating Token Index: 981

Text #7

Max Range: 4.3916. Min Range: -4.3916

Max Act: 4.2127. Min Act: -0.1700

Data Index: 7509968 (Open Web Text)

Max Activating Token Index: 328

Text #8

Max Range: 4.3916. Min Range: -4.3916

Max Act: 4.1505. Min Act: -0.1700

Data Index: 3254057 (Open Web Text)

Max Activating Token Index: 950

Text #9

Max Range: 4.3916. Min Range: -4.3916

Max Act: 4.1750. Min Act: -0.1700

Data Index: 4918771 (Open Web Text)

Max Activating Token Index: 944

Text #10

Max Range: 4.3916. Min Range: -4.3916

Max Act: 4.1539. Min Act: -0.1700

Data Index: 3587731 (Open Web Text)

Max Activating Token Index: 784

Text #11

Max Range: 4.3916. Min Range: -4.3916

Max Act: 4.1627. Min Act: -0.1700

Data Index: 7262865 (Open Web Text)

Max Activating Token Index: 655

Text #12

Max Range: 4.3916. Min Range: -4.3916

Max Act: 4.1448. Min Act: -0.1700

Data Index: 1906898 (Open Web Text)

Max Activating Token Index: 854

Text #13

Max Range: 4.3916. Min Range: -4.3916

Max Act: 4.1732. Min Act: -0.1700

Data Index: 8602056 (Open Web Text)

Max Activating Token Index: 1008

Text #14

Max Range: 4.3916. Min Range: -4.3916

Max Act: 4.1486. Min Act: -0.1700

Data Index: 8019553 (Open Web Text)

Max Activating Token Index: 575

Text #15

Max Range: 4.3916. Min Range: -4.3916

Max Act: 4.1195. Min Act: -0.1700

Data Index: 6943891 (Open Web Text)

Max Activating Token Index: 535

Text #16

Max Range: 4.3916. Min Range: -4.3916

Max Act: 4.1584. Min Act: -0.1700

Data Index: 2202365 (Open Web Text)

Max Activating Token Index: 781

Text #17

Max Range: 4.3916. Min Range: -4.3916

Max Act: 4.1464. Min Act: -0.1700

Data Index: 1380264 (Open Web Text)

Max Activating Token Index: 558

Text #18

Max Range: 4.3916. Min Range: -4.3916

Max Act: 4.1407. Min Act: -0.1700

Data Index: 4307030 (Open Web Text)

Max Activating Token Index: 323

Text #19

Max Range: 4.3916. Min Range: -4.3916

Max Act: 4.1404. Min Act: -0.1700

Data Index: 7300592 (Open Web Text)

Max Activating Token Index: 967