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

Dataset: Open Web Text

Neuron 2536 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: 4.9466. Min Range: -4.9466

Max Act: 4.9466. Min Act: -0.1700

Data Index: 970522 (Open Web Text)

Max Activating Token Index: 562

Text #1

Max Range: 4.9466. Min Range: -4.9466

Max Act: 4.8861. Min Act: -0.1700

Data Index: 2500056 (Open Web Text)

Max Activating Token Index: 43

Text #2

Max Range: 4.9466. Min Range: -4.9466

Max Act: 4.8078. Min Act: -0.1700

Data Index: 6737305 (Open Web Text)

Max Activating Token Index: 332

Text #3

Max Range: 4.9466. Min Range: -4.9466

Max Act: 4.8042. Min Act: -0.1700

Data Index: 4608442 (Open Web Text)

Max Activating Token Index: 1017

Text #4

Max Range: 4.9466. Min Range: -4.9466

Max Act: 4.7922. Min Act: -0.1700

Data Index: 8476799 (Open Web Text)

Max Activating Token Index: 849

Text #5

Max Range: 4.9466. Min Range: -4.9466

Max Act: 4.8247. Min Act: -0.1700

Data Index: 4354438 (Open Web Text)

Max Activating Token Index: 487

Text #6

Max Range: 4.9466. Min Range: -4.9466

Max Act: 4.7721. Min Act: -0.1700

Data Index: 4369112 (Open Web Text)

Max Activating Token Index: 379

Text #7

Max Range: 4.9466. Min Range: -4.9466

Max Act: 4.7858. Min Act: -0.1700

Data Index: 4823304 (Open Web Text)

Max Activating Token Index: 603

Text #8

Max Range: 4.9466. Min Range: -4.9466

Max Act: 4.7381. Min Act: -0.1700

Data Index: 1075479 (Open Web Text)

Max Activating Token Index: 39

Text #9

Max Range: 4.9466. Min Range: -4.9466

Max Act: 4.7379. Min Act: -0.1700

Data Index: 1530144 (Open Web Text)

Max Activating Token Index: 993

Text #10

Max Range: 4.9466. Min Range: -4.9466

Max Act: 4.7716. Min Act: -0.1700

Data Index: 1474619 (Open Web Text)

Max Activating Token Index: 478

Text #11

Max Range: 4.9466. Min Range: -4.9466

Max Act: 4.7330. Min Act: -0.1700

Data Index: 5810117 (Open Web Text)

Max Activating Token Index: 463

Text #12

Max Range: 4.9466. Min Range: -4.9466

Max Act: 4.7396. Min Act: -0.1700

Data Index: 2083613 (Open Web Text)

Max Activating Token Index: 952

Text #13

Max Range: 4.9466. Min Range: -4.9466

Max Act: 4.7528. Min Act: -0.1700

Data Index: 6796526 (Open Web Text)

Max Activating Token Index: 361

Text #14

Max Range: 4.9466. Min Range: -4.9466

Max Act: 4.7594. Min Act: -0.1700

Data Index: 6600917 (Open Web Text)

Max Activating Token Index: 219

Text #15

Max Range: 4.9466. Min Range: -4.9466

Max Act: 4.7217. Min Act: -0.1700

Data Index: 2808808 (Open Web Text)

Max Activating Token Index: 319

Text #16

Max Range: 4.9466. Min Range: -4.9466

Max Act: 4.6827. Min Act: -0.1700

Data Index: 1423672 (Open Web Text)

Max Activating Token Index: 496

Text #17

Max Range: 4.9466. Min Range: -4.9466

Max Act: 4.7014. Min Act: -0.1700

Data Index: 5431011 (Open Web Text)

Max Activating Token Index: 465

Text #18

Max Range: 4.9466. Min Range: -4.9466

Max Act: 4.7198. Min Act: -0.1700

Data Index: 890700 (Open Web Text)

Max Activating Token Index: 800

Text #19

Max Range: 4.9466. Min Range: -4.9466

Max Act: 4.7151. Min Act: -0.1700

Data Index: 4357531 (Open Web Text)

Max Activating Token Index: 659