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

Dataset: Open Web Text

Neuron 2560 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: 5.9514. Min Range: -5.9514

Max Act: 5.9514. Min Act: -0.1700

Data Index: 6834796 (Open Web Text)

Max Activating Token Index: 226

Text #1

Max Range: 5.9514. Min Range: -5.9514

Max Act: 5.8388. Min Act: -0.1700

Data Index: 7370484 (Open Web Text)

Max Activating Token Index: 522

Text #2

Max Range: 5.9514. Min Range: -5.9514

Max Act: 5.8020. Min Act: -0.1700

Data Index: 7722486 (Open Web Text)

Max Activating Token Index: 511

Text #3

Max Range: 5.9514. Min Range: -5.9514

Max Act: 5.6902. Min Act: -0.1700

Data Index: 8277189 (Open Web Text)

Max Activating Token Index: 954

Text #4

Max Range: 5.9514. Min Range: -5.9514

Max Act: 5.7010. Min Act: -0.1700

Data Index: 8671815 (Open Web Text)

Max Activating Token Index: 621

Text #5

Max Range: 5.9514. Min Range: -5.9514

Max Act: 5.6127. Min Act: -0.1700

Data Index: 5826698 (Open Web Text)

Max Activating Token Index: 815

Text #6

Max Range: 5.9514. Min Range: -5.9514

Max Act: 5.5823. Min Act: -0.1700

Data Index: 7868319 (Open Web Text)

Max Activating Token Index: 604

Text #7

Max Range: 5.9514. Min Range: -5.9514

Max Act: 5.5867. Min Act: -0.1700

Data Index: 3518227 (Open Web Text)

Max Activating Token Index: 160

Text #8

Max Range: 5.9514. Min Range: -5.9514

Max Act: 5.5186. Min Act: -0.1700

Data Index: 7381782 (Open Web Text)

Max Activating Token Index: 379

Text #9

Max Range: 5.9514. Min Range: -5.9514

Max Act: 5.5300. Min Act: -0.1700

Data Index: 2530689 (Open Web Text)

Max Activating Token Index: 493

Text #10

Max Range: 5.9514. Min Range: -5.9514

Max Act: 5.5122. Min Act: -0.1700

Data Index: 8592451 (Open Web Text)

Max Activating Token Index: 530

Text #11

Max Range: 5.9514. Min Range: -5.9514

Max Act: 5.5308. Min Act: -0.1700

Data Index: 7022696 (Open Web Text)

Max Activating Token Index: 341

Text #12

Max Range: 5.9514. Min Range: -5.9514

Max Act: 5.5311. Min Act: -0.1700

Data Index: 1790313 (Open Web Text)

Max Activating Token Index: 604

Text #13

Max Range: 5.9514. Min Range: -5.9514

Max Act: 5.4882. Min Act: -0.1700

Data Index: 3650831 (Open Web Text)

Max Activating Token Index: 848

Text #14

Max Range: 5.9514. Min Range: -5.9514

Max Act: 5.4847. Min Act: -0.1700

Data Index: 2140229 (Open Web Text)

Max Activating Token Index: 289

Text #15

Max Range: 5.9514. Min Range: -5.9514

Max Act: 5.5187. Min Act: -0.1700

Data Index: 6899244 (Open Web Text)

Max Activating Token Index: 428

Text #16

Max Range: 5.9514. Min Range: -5.9514

Max Act: 5.4985. Min Act: -0.1700

Data Index: 6636489 (Open Web Text)

Max Activating Token Index: 290

Text #17

Max Range: 5.9514. Min Range: -5.9514

Max Act: 5.4776. Min Act: -0.1700

Data Index: 4162557 (Open Web Text)

Max Activating Token Index: 349

Text #18

Max Range: 5.9514. Min Range: -5.9514

Max Act: 5.4841. Min Act: -0.1700

Data Index: 6188432 (Open Web Text)

Max Activating Token Index: 851

Text #19

Max Range: 5.9514. Min Range: -5.9514

Max Act: 5.4655. Min Act: -0.1700

Data Index: 3396026 (Open Web Text)

Max Activating Token Index: 90