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

Dataset: Open Web Text

Neuron 821 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: 7.9683. Min Range: -7.9683

Max Act: 7.9581. Min Act: -0.1699

Data Index: 5769218 (Open Web Text)

Max Activating Token Index: 353

Text #1

Max Range: 7.9683. Min Range: -7.9683

Max Act: 7.9683. Min Act: -0.1700

Data Index: 6602869 (Open Web Text)

Max Activating Token Index: 428

Text #2

Max Range: 7.9683. Min Range: -7.9683

Max Act: 7.6156. Min Act: -0.1700

Data Index: 1155593 (Open Web Text)

Max Activating Token Index: 536

Text #3

Max Range: 7.9683. Min Range: -7.9683

Max Act: 7.5220. Min Act: -0.1700

Data Index: 831766 (Open Web Text)

Max Activating Token Index: 956

Text #4

Max Range: 7.9683. Min Range: -7.9683

Max Act: 7.5773. Min Act: -0.1695

Data Index: 5936973 (Open Web Text)

Max Activating Token Index: 340

Text #5

Max Range: 7.9683. Min Range: -7.9683

Max Act: 7.5686. Min Act: -0.1700

Data Index: 477665 (Open Web Text)

Max Activating Token Index: 752

Text #6

Max Range: 7.9683. Min Range: -7.9683

Max Act: 7.5856. Min Act: -0.1700

Data Index: 2670317 (Open Web Text)

Max Activating Token Index: 490

Text #7

Max Range: 7.9683. Min Range: -7.9683

Max Act: 7.5667. Min Act: -0.1700

Data Index: 8247103 (Open Web Text)

Max Activating Token Index: 680

Text #8

Max Range: 7.9683. Min Range: -7.9683

Max Act: 7.5187. Min Act: -0.1700

Data Index: 1767087 (Open Web Text)

Max Activating Token Index: 722

Text #9

Max Range: 7.9683. Min Range: -7.9683

Max Act: 7.4627. Min Act: -0.1694

Data Index: 297209 (Open Web Text)

Max Activating Token Index: 501

Text #10

Max Range: 7.9683. Min Range: -7.9683

Max Act: 7.3692. Min Act: -0.1700

Data Index: 5260958 (Open Web Text)

Max Activating Token Index: 242

Text #11

Max Range: 7.9683. Min Range: -7.9683

Max Act: 7.4441. Min Act: -0.1700

Data Index: 1828949 (Open Web Text)

Max Activating Token Index: 486

Text #12

Max Range: 7.9683. Min Range: -7.9683

Max Act: 7.4138. Min Act: -0.1700

Data Index: 1417106 (Open Web Text)

Max Activating Token Index: 609

Text #13

Max Range: 7.9683. Min Range: -7.9683

Max Act: 7.3845. Min Act: -0.1700

Data Index: 6518648 (Open Web Text)

Max Activating Token Index: 937

Text #14

Max Range: 7.9683. Min Range: -7.9683

Max Act: 7.1716. Min Act: -0.1700

Data Index: 6385425 (Open Web Text)

Max Activating Token Index: 459

Text #15

Max Range: 7.9683. Min Range: -7.9683

Max Act: 7.3560. Min Act: -0.1700

Data Index: 8342025 (Open Web Text)

Max Activating Token Index: 245

Text #16

Max Range: 7.9683. Min Range: -7.9683

Max Act: 7.2304. Min Act: -0.1700

Data Index: 6019842 (Open Web Text)

Max Activating Token Index: 575

Text #17

Max Range: 7.9683. Min Range: -7.9683

Max Act: 7.2613. Min Act: -0.1699

Data Index: 5550889 (Open Web Text)

Max Activating Token Index: 938

Text #18

Max Range: 7.9683. Min Range: -7.9683

Max Act: 7.2302. Min Act: -0.1700

Data Index: 8279816 (Open Web Text)

Max Activating Token Index: 890

Text #19

Max Range: 7.9683. Min Range: -7.9683

Max Act: 7.1865. Min Act: -0.1698

Data Index: 4164808 (Open Web Text)

Max Activating Token Index: 300