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

Dataset: Open Web Text

Neuron 1226 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: 1.9391. Min Range: -1.9391

Max Act: 1.9391. Min Act: -0.1700

Data Index: 8415225 (Open Web Text)

Max Activating Token Index: 699

Text #1

Max Range: 1.9391. Min Range: -1.9391

Max Act: 1.9124. Min Act: -0.1700

Data Index: 3930754 (Open Web Text)

Max Activating Token Index: 359

Text #2

Max Range: 1.9391. Min Range: -1.9391

Max Act: 1.9144. Min Act: -0.1700

Data Index: 370564 (Open Web Text)

Max Activating Token Index: 749

Text #3

Max Range: 1.9391. Min Range: -1.9391

Max Act: 1.9196. Min Act: -0.1700

Data Index: 1385220 (Open Web Text)

Max Activating Token Index: 713

Text #4

Max Range: 1.9391. Min Range: -1.9391

Max Act: 1.9075. Min Act: -0.1700

Data Index: 6129070 (Open Web Text)

Max Activating Token Index: 591

Text #5

Max Range: 1.9391. Min Range: -1.9391

Max Act: 1.9033. Min Act: -0.1700

Data Index: 4012786 (Open Web Text)

Max Activating Token Index: 628

Text #6

Max Range: 1.9391. Min Range: -1.9391

Max Act: 1.8982. Min Act: -0.1700

Data Index: 4870808 (Open Web Text)

Max Activating Token Index: 341

Text #7

Max Range: 1.9391. Min Range: -1.9391

Max Act: 1.8967. Min Act: -0.1700

Data Index: 1399631 (Open Web Text)

Max Activating Token Index: 934

Text #8

Max Range: 1.9391. Min Range: -1.9391

Max Act: 1.8908. Min Act: -0.1700

Data Index: 7865245 (Open Web Text)

Max Activating Token Index: 104

Text #9

Max Range: 1.9391. Min Range: -1.9391

Max Act: 1.8893. Min Act: -0.1700

Data Index: 4429631 (Open Web Text)

Max Activating Token Index: 660

Text #10

Max Range: 1.9391. Min Range: -1.9391

Max Act: 1.8876. Min Act: -0.1700

Data Index: 5473588 (Open Web Text)

Max Activating Token Index: 756

Text #11

Max Range: 1.9391. Min Range: -1.9391

Max Act: 1.8779. Min Act: -0.1700

Data Index: 6251068 (Open Web Text)

Max Activating Token Index: 660

Text #12

Max Range: 1.9391. Min Range: -1.9391

Max Act: 1.8924. Min Act: -0.1700

Data Index: 7104482 (Open Web Text)

Max Activating Token Index: 254

Text #13

Max Range: 1.9391. Min Range: -1.9391

Max Act: 1.8805. Min Act: -0.1700

Data Index: 8316170 (Open Web Text)

Max Activating Token Index: 457

Text #14

Max Range: 1.9391. Min Range: -1.9391

Max Act: 1.8806. Min Act: -0.1700

Data Index: 7981470 (Open Web Text)

Max Activating Token Index: 540

Text #15

Max Range: 1.9391. Min Range: -1.9391

Max Act: 1.8787. Min Act: -0.1700

Data Index: 6535963 (Open Web Text)

Max Activating Token Index: 935

Text #16

Max Range: 1.9391. Min Range: -1.9391

Max Act: 1.8839. Min Act: -0.1700

Data Index: 8118596 (Open Web Text)

Max Activating Token Index: 407

Text #17

Max Range: 1.9391. Min Range: -1.9391

Max Act: 1.8794. Min Act: -0.1700

Data Index: 1287663 (Open Web Text)

Max Activating Token Index: 658

Text #18

Max Range: 1.9391. Min Range: -1.9391

Max Act: 1.8887. Min Act: -0.1700

Data Index: 3304481 (Open Web Text)

Max Activating Token Index: 680

Text #19

Max Range: 1.9391. Min Range: -1.9391

Max Act: 1.8808. Min Act: -0.1700

Data Index: 6902052 (Open Web Text)

Max Activating Token Index: 443