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

Dataset: Open Web Text

Neuron 2500 in Layer 3

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: 4.2491. Min Range: -4.2491

Max Act: 4.2491. Min Act: -0.1700

Data Index: 6584884 (Open Web Text)

Max Activating Token Index: 379

Text #1

Max Range: 4.2491. Min Range: -4.2491

Max Act: 4.2312. Min Act: -0.1700

Data Index: 8152691 (Open Web Text)

Max Activating Token Index: 685

Text #2

Max Range: 4.2491. Min Range: -4.2491

Max Act: 4.2222. Min Act: -0.1700

Data Index: 4325949 (Open Web Text)

Max Activating Token Index: 204

Text #3

Max Range: 4.2491. Min Range: -4.2491

Max Act: 4.2043. Min Act: -0.1700

Data Index: 8273887 (Open Web Text)

Max Activating Token Index: 273

Text #4

Max Range: 4.2491. Min Range: -4.2491

Max Act: 4.1684. Min Act: -0.1700

Data Index: 8740247 (Open Web Text)

Max Activating Token Index: 799

Text #5

Max Range: 4.2491. Min Range: -4.2491

Max Act: 4.1418. Min Act: -0.1700

Data Index: 980930 (Open Web Text)

Max Activating Token Index: 625

Text #6

Max Range: 4.2491. Min Range: -4.2491

Max Act: 4.1319. Min Act: -0.1700

Data Index: 2129887 (Open Web Text)

Max Activating Token Index: 737

Text #7

Max Range: 4.2491. Min Range: -4.2491

Max Act: 4.1488. Min Act: -0.1700

Data Index: 803919 (Open Web Text)

Max Activating Token Index: 24

Text #8

Max Range: 4.2491. Min Range: -4.2491

Max Act: 4.1309. Min Act: -0.1700

Data Index: 7822026 (Open Web Text)

Max Activating Token Index: 714

Text #9

Max Range: 4.2491. Min Range: -4.2491

Max Act: 4.1588. Min Act: -0.1700

Data Index: 1817626 (Open Web Text)

Max Activating Token Index: 596

Text #10

Max Range: 4.2491. Min Range: -4.2491

Max Act: 4.1587. Min Act: -0.1700

Data Index: 186558 (Open Web Text)

Max Activating Token Index: 753

Text #11

Max Range: 4.2491. Min Range: -4.2491

Max Act: 4.1433. Min Act: -0.1700

Data Index: 1615606 (Open Web Text)

Max Activating Token Index: 268

Text #12

Max Range: 4.2491. Min Range: -4.2491

Max Act: 4.1447. Min Act: -0.1700

Data Index: 4224527 (Open Web Text)

Max Activating Token Index: 460

Text #13

Max Range: 4.2491. Min Range: -4.2491

Max Act: 4.1454. Min Act: -0.1700

Data Index: 5831468 (Open Web Text)

Max Activating Token Index: 611

Text #14

Max Range: 4.2491. Min Range: -4.2491

Max Act: 4.1580. Min Act: -0.1700

Data Index: 851735 (Open Web Text)

Max Activating Token Index: 776

Text #15

Max Range: 4.2491. Min Range: -4.2491

Max Act: 4.1139. Min Act: -0.1700

Data Index: 4378593 (Open Web Text)

Max Activating Token Index: 512

Text #16

Max Range: 4.2491. Min Range: -4.2491

Max Act: 4.1074. Min Act: -0.1700

Data Index: 2374491 (Open Web Text)

Max Activating Token Index: 969

Text #17

Max Range: 4.2491. Min Range: -4.2491

Max Act: 4.0985. Min Act: -0.1700

Data Index: 554613 (Open Web Text)

Max Activating Token Index: 472

Text #18

Max Range: 4.2491. Min Range: -4.2491

Max Act: 4.0745. Min Act: -0.1700

Data Index: 5818337 (Open Web Text)

Max Activating Token Index: 67

Text #19

Max Range: 4.2491. Min Range: -4.2491

Max Act: 4.0857. Min Act: -0.1700

Data Index: 1404077 (Open Web Text)

Max Activating Token Index: 541