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

Dataset: Open Web Text

Neuron 1769 in Layer 4

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: 1.8309. Min Range: -1.8309

Max Act: 1.8309. Min Act: -0.1700

Data Index: 400477 (Open Web Text)

Max Activating Token Index: 589

Text #1

Max Range: 1.8309. Min Range: -1.8309

Max Act: 1.8232. Min Act: -0.1700

Data Index: 8445587 (Open Web Text)

Max Activating Token Index: 403

Text #2

Max Range: 1.8309. Min Range: -1.8309

Max Act: 1.8018. Min Act: -0.1700

Data Index: 886176 (Open Web Text)

Max Activating Token Index: 561

Text #3

Max Range: 1.8309. Min Range: -1.8309

Max Act: 1.7912. Min Act: -0.1700

Data Index: 4916539 (Open Web Text)

Max Activating Token Index: 388

Text #4

Max Range: 1.8309. Min Range: -1.8309

Max Act: 1.7904. Min Act: -0.1700

Data Index: 2713572 (Open Web Text)

Max Activating Token Index: 532

Text #5

Max Range: 1.8309. Min Range: -1.8309

Max Act: 1.7798. Min Act: -0.1700

Data Index: 400483 (Open Web Text)

Max Activating Token Index: 776

Text #6

Max Range: 1.8309. Min Range: -1.8309

Max Act: 1.7587. Min Act: -0.1700

Data Index: 2723926 (Open Web Text)

Max Activating Token Index: 440

Text #7

Max Range: 1.8309. Min Range: -1.8309

Max Act: 1.7683. Min Act: -0.1700

Data Index: 827152 (Open Web Text)

Max Activating Token Index: 140

Text #8

Max Range: 1.8309. Min Range: -1.8309

Max Act: 1.7606. Min Act: -0.1700

Data Index: 400479 (Open Web Text)

Max Activating Token Index: 839

Text #9

Max Range: 1.8309. Min Range: -1.8309

Max Act: 1.7774. Min Act: -0.1700

Data Index: 3556940 (Open Web Text)

Max Activating Token Index: 589

Text #10

Max Range: 1.8309. Min Range: -1.8309

Max Act: 1.7454. Min Act: -0.1700

Data Index: 8087524 (Open Web Text)

Max Activating Token Index: 39

Text #11

Max Range: 1.8309. Min Range: -1.8309

Max Act: 1.7693. Min Act: -0.1698

Data Index: 400482 (Open Web Text)

Max Activating Token Index: 978

Text #12

Max Range: 1.8309. Min Range: -1.8309

Max Act: 1.7532. Min Act: -0.1700

Data Index: 257793 (Open Web Text)

Max Activating Token Index: 547

Text #13

Max Range: 1.8309. Min Range: -1.8309

Max Act: 1.7635. Min Act: -0.1700

Data Index: 8366250 (Open Web Text)

Max Activating Token Index: 486

Text #14

Max Range: 1.8309. Min Range: -1.8309

Max Act: 1.7417. Min Act: -0.1700

Data Index: 1977310 (Open Web Text)

Max Activating Token Index: 566

Text #15

Max Range: 1.8309. Min Range: -1.8309

Max Act: 1.7364. Min Act: -0.1700

Data Index: 378247 (Open Web Text)

Max Activating Token Index: 160

Text #16

Max Range: 1.8309. Min Range: -1.8309

Max Act: 1.7266. Min Act: -0.1700

Data Index: 2868010 (Open Web Text)

Max Activating Token Index: 891

Text #17

Max Range: 1.8309. Min Range: -1.8309

Max Act: 1.7260. Min Act: -0.1700

Data Index: 5209512 (Open Web Text)

Max Activating Token Index: 390

Text #18

Max Range: 1.8309. Min Range: -1.8309

Max Act: 1.7420. Min Act: -0.1698

Data Index: 886172 (Open Web Text)

Max Activating Token Index: 763

Text #19

Max Range: 1.8309. Min Range: -1.8309

Max Act: 1.7137. Min Act: -0.1700

Data Index: 3048789 (Open Web Text)

Max Activating Token Index: 880