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

Dataset: Open Web Text

Neuron 2269 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: 3.9590. Min Range: -3.9590

Max Act: 3.9590. Min Act: -0.1700

Data Index: 7712881 (Open Web Text)

Max Activating Token Index: 656

Text #1

Max Range: 3.9590. Min Range: -3.9590

Max Act: 3.8875. Min Act: -0.1700

Data Index: 1581003 (Open Web Text)

Max Activating Token Index: 237

Text #2

Max Range: 3.9590. Min Range: -3.9590

Max Act: 3.8334. Min Act: -0.1700

Data Index: 6454308 (Open Web Text)

Max Activating Token Index: 397

Text #3

Max Range: 3.9590. Min Range: -3.9590

Max Act: 3.8030. Min Act: -0.1700

Data Index: 2418338 (Open Web Text)

Max Activating Token Index: 1014

Text #4

Max Range: 3.9590. Min Range: -3.9590

Max Act: 3.8151. Min Act: -0.1700

Data Index: 6937690 (Open Web Text)

Max Activating Token Index: 621

Text #5

Max Range: 3.9590. Min Range: -3.9590

Max Act: 3.8220. Min Act: -0.1700

Data Index: 8557822 (Open Web Text)

Max Activating Token Index: 64

Text #6

Max Range: 3.9590. Min Range: -3.9590

Max Act: 3.7948. Min Act: -0.1700

Data Index: 8375181 (Open Web Text)

Max Activating Token Index: 340

Text #7

Max Range: 3.9590. Min Range: -3.9590

Max Act: 3.8022. Min Act: -0.1700

Data Index: 3447222 (Open Web Text)

Max Activating Token Index: 600

Text #8

Max Range: 3.9590. Min Range: -3.9590

Max Act: 3.8381. Min Act: -0.1700

Data Index: 1367713 (Open Web Text)

Max Activating Token Index: 568

Text #9

Max Range: 3.9590. Min Range: -3.9590

Max Act: 3.8502. Min Act: -0.1700

Data Index: 7326356 (Open Web Text)

Max Activating Token Index: 1021

Text #10

Max Range: 3.9590. Min Range: -3.9590

Max Act: 3.7838. Min Act: -0.1700

Data Index: 5662549 (Open Web Text)

Max Activating Token Index: 890

Text #11

Max Range: 3.9590. Min Range: -3.9590

Max Act: 3.7899. Min Act: -0.1700

Data Index: 1701154 (Open Web Text)

Max Activating Token Index: 351

Text #12

Max Range: 3.9590. Min Range: -3.9590

Max Act: 3.8257. Min Act: -0.1700

Data Index: 3521983 (Open Web Text)

Max Activating Token Index: 381

Text #13

Max Range: 3.9590. Min Range: -3.9590

Max Act: 3.7982. Min Act: -0.1700

Data Index: 3886106 (Open Web Text)

Max Activating Token Index: 383

Text #14

Max Range: 3.9590. Min Range: -3.9590

Max Act: 3.8155. Min Act: -0.1700

Data Index: 6712516 (Open Web Text)

Max Activating Token Index: 641

Text #15

Max Range: 3.9590. Min Range: -3.9590

Max Act: 3.7493. Min Act: -0.1700

Data Index: 5380067 (Open Web Text)

Max Activating Token Index: 358

Text #16

Max Range: 3.9590. Min Range: -3.9590

Max Act: 3.7752. Min Act: -0.1700

Data Index: 5558572 (Open Web Text)

Max Activating Token Index: 515

Text #17

Max Range: 3.9590. Min Range: -3.9590

Max Act: 3.7701. Min Act: -0.1700

Data Index: 3617911 (Open Web Text)

Max Activating Token Index: 192

Text #18

Max Range: 3.9590. Min Range: -3.9590

Max Act: 3.7500. Min Act: -0.1700

Data Index: 2535199 (Open Web Text)

Max Activating Token Index: 908

Text #19

Max Range: 3.9590. Min Range: -3.9590

Max Act: 3.7678. Min Act: -0.1700

Data Index: 7269817 (Open Web Text)

Max Activating Token Index: 52