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

Dataset: Open Web Text

Neuron 967 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: 2.0306. Min Range: -2.0306

Max Act: 2.0234. Min Act: -0.1700

Data Index: 866085 (Open Web Text)

Max Activating Token Index: 279

Text #1

Max Range: 2.0306. Min Range: -2.0306

Max Act: 2.0306. Min Act: -0.1700

Data Index: 5307626 (Open Web Text)

Max Activating Token Index: 342

Text #2

Max Range: 2.0306. Min Range: -2.0306

Max Act: 1.9343. Min Act: -0.1700

Data Index: 4381510 (Open Web Text)

Max Activating Token Index: 503

Text #3

Max Range: 2.0306. Min Range: -2.0306

Max Act: 1.9251. Min Act: -0.1700

Data Index: 4122427 (Open Web Text)

Max Activating Token Index: 102

Text #4

Max Range: 2.0306. Min Range: -2.0306

Max Act: 1.9271. Min Act: -0.1700

Data Index: 2767269 (Open Web Text)

Max Activating Token Index: 25

Text #5

Max Range: 2.0306. Min Range: -2.0306

Max Act: 1.9297. Min Act: -0.1700

Data Index: 6267068 (Open Web Text)

Max Activating Token Index: 794

Text #6

Max Range: 2.0306. Min Range: -2.0306

Max Act: 1.9205. Min Act: -0.1700

Data Index: 6419176 (Open Web Text)

Max Activating Token Index: 744

Text #7

Max Range: 2.0306. Min Range: -2.0306

Max Act: 1.9196. Min Act: -0.1699

Data Index: 553539 (Open Web Text)

Max Activating Token Index: 77

Text #8

Max Range: 2.0306. Min Range: -2.0306

Max Act: 1.9028. Min Act: -0.1700

Data Index: 4067504 (Open Web Text)

Max Activating Token Index: 288

Text #9

Max Range: 2.0306. Min Range: -2.0306

Max Act: 1.9140. Min Act: -0.1700

Data Index: 3485152 (Open Web Text)

Max Activating Token Index: 680

Text #10

Max Range: 2.0306. Min Range: -2.0306

Max Act: 1.8790. Min Act: -0.1700

Data Index: 3092759 (Open Web Text)

Max Activating Token Index: 111

Text #11

Max Range: 2.0306. Min Range: -2.0306

Max Act: 1.8880. Min Act: -0.1695

Data Index: 1532782 (Open Web Text)

Max Activating Token Index: 385

Text #12

Max Range: 2.0306. Min Range: -2.0306

Max Act: 1.8821. Min Act: -0.1700

Data Index: 6817015 (Open Web Text)

Max Activating Token Index: 89

Text #13

Max Range: 2.0306. Min Range: -2.0306

Max Act: 1.8868. Min Act: -0.1700

Data Index: 8237127 (Open Web Text)

Max Activating Token Index: 268

Text #14

Max Range: 2.0306. Min Range: -2.0306

Max Act: 1.8873. Min Act: -0.1700

Data Index: 1387650 (Open Web Text)

Max Activating Token Index: 499

Text #15

Max Range: 2.0306. Min Range: -2.0306

Max Act: 1.8802. Min Act: -0.1700

Data Index: 6441779 (Open Web Text)

Max Activating Token Index: 22

Text #16

Max Range: 2.0306. Min Range: -2.0306

Max Act: 1.8668. Min Act: -0.1700

Data Index: 4491692 (Open Web Text)

Max Activating Token Index: 783

Text #17

Max Range: 2.0306. Min Range: -2.0306

Max Act: 1.8624. Min Act: -0.1700

Data Index: 2296925 (Open Web Text)

Max Activating Token Index: 489

Text #18

Max Range: 2.0306. Min Range: -2.0306

Max Act: 1.8654. Min Act: -0.1700

Data Index: 7095028 (Open Web Text)

Max Activating Token Index: 300

Text #19

Max Range: 2.0306. Min Range: -2.0306

Max Act: 1.8753. Min Act: -0.1700

Data Index: 5061395 (Open Web Text)

Max Activating Token Index: 50