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

Dataset: Open Web Text

Neuron 743 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: 6.0339. Min Range: -6.0339

Max Act: 6.0339. Min Act: -0.1700

Data Index: 7895354 (Open Web Text)

Max Activating Token Index: 13

Text #1

Max Range: 6.0339. Min Range: -6.0339

Max Act: 5.8806. Min Act: -0.1700

Data Index: 2380604 (Open Web Text)

Max Activating Token Index: 379

Text #2

Max Range: 6.0339. Min Range: -6.0339

Max Act: 5.8436. Min Act: -0.1700

Data Index: 2888421 (Open Web Text)

Max Activating Token Index: 340

Text #3

Max Range: 6.0339. Min Range: -6.0339

Max Act: 5.8084. Min Act: -0.1700

Data Index: 6008055 (Open Web Text)

Max Activating Token Index: 879

Text #4

Max Range: 6.0339. Min Range: -6.0339

Max Act: 5.7627. Min Act: -0.1700

Data Index: 7087021 (Open Web Text)

Max Activating Token Index: 13

Text #5

Max Range: 6.0339. Min Range: -6.0339

Max Act: 5.6849. Min Act: -0.1700

Data Index: 6478272 (Open Web Text)

Max Activating Token Index: 21

Text #6

Max Range: 6.0339. Min Range: -6.0339

Max Act: 5.7123. Min Act: -0.1700

Data Index: 8735218 (Open Web Text)

Max Activating Token Index: 339

Text #7

Max Range: 6.0339. Min Range: -6.0339

Max Act: 5.7565. Min Act: -0.1700

Data Index: 6342813 (Open Web Text)

Max Activating Token Index: 886

Text #8

Max Range: 6.0339. Min Range: -6.0339

Max Act: 5.7010. Min Act: -0.1700

Data Index: 565390 (Open Web Text)

Max Activating Token Index: 326

Text #9

Max Range: 6.0339. Min Range: -6.0339

Max Act: 5.6833. Min Act: -0.1700

Data Index: 8585558 (Open Web Text)

Max Activating Token Index: 921

Text #10

Max Range: 6.0339. Min Range: -6.0339

Max Act: 5.5856. Min Act: -0.1700

Data Index: 7527504 (Open Web Text)

Max Activating Token Index: 721

Text #11

Max Range: 6.0339. Min Range: -6.0339

Max Act: 5.6195. Min Act: -0.1700

Data Index: 3902778 (Open Web Text)

Max Activating Token Index: 335

Text #12

Max Range: 6.0339. Min Range: -6.0339

Max Act: 5.6255. Min Act: -0.1700

Data Index: 2236229 (Open Web Text)

Max Activating Token Index: 212

Text #13

Max Range: 6.0339. Min Range: -6.0339

Max Act: 5.5720. Min Act: -0.1700

Data Index: 5069980 (Open Web Text)

Max Activating Token Index: 354

Text #14

Max Range: 6.0339. Min Range: -6.0339

Max Act: 5.5865. Min Act: -0.1700

Data Index: 927194 (Open Web Text)

Max Activating Token Index: 833

Text #15

Max Range: 6.0339. Min Range: -6.0339

Max Act: 5.5766. Min Act: -0.1700

Data Index: 903189 (Open Web Text)

Max Activating Token Index: 223

Text #16

Max Range: 6.0339. Min Range: -6.0339

Max Act: 5.5832. Min Act: -0.1700

Data Index: 8706202 (Open Web Text)

Max Activating Token Index: 59

Text #17

Max Range: 6.0339. Min Range: -6.0339

Max Act: 5.5785. Min Act: -0.1700

Data Index: 7131254 (Open Web Text)

Max Activating Token Index: 157

Text #18

Max Range: 6.0339. Min Range: -6.0339

Max Act: 5.5374. Min Act: -0.1700

Data Index: 1086231 (Open Web Text)

Max Activating Token Index: 29

Text #19

Max Range: 6.0339. Min Range: -6.0339

Max Act: 5.5417. Min Act: -0.1700

Data Index: 2734449 (Open Web Text)

Max Activating Token Index: 224