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

Dataset: Open Web Text

Neuron 177 in Layer 1

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: 4.8606. Min Range: -4.8606

Max Act: 4.8562. Min Act: -0.1700

Data Index: 3937237 (Open Web Text)

Max Activating Token Index: 655

Text #1

Max Range: 4.8606. Min Range: -4.8606

Max Act: 4.8606. Min Act: -0.1700

Data Index: 7323628 (Open Web Text)

Max Activating Token Index: 741

Text #2

Max Range: 4.8606. Min Range: -4.8606

Max Act: 4.8304. Min Act: -0.1700

Data Index: 5514021 (Open Web Text)

Max Activating Token Index: 550

Text #3

Max Range: 4.8606. Min Range: -4.8606

Max Act: 4.8449. Min Act: -0.1700

Data Index: 8283870 (Open Web Text)

Max Activating Token Index: 567

Text #4

Max Range: 4.8606. Min Range: -4.8606

Max Act: 4.8053. Min Act: -0.1700

Data Index: 4293030 (Open Web Text)

Max Activating Token Index: 316

Text #5

Max Range: 4.8606. Min Range: -4.8606

Max Act: 4.8014. Min Act: -0.1700

Data Index: 2752678 (Open Web Text)

Max Activating Token Index: 218

Text #6

Max Range: 4.8606. Min Range: -4.8606

Max Act: 4.8009. Min Act: -0.1700

Data Index: 5466875 (Open Web Text)

Max Activating Token Index: 591

Text #7

Max Range: 4.8606. Min Range: -4.8606

Max Act: 4.7930. Min Act: -0.1700

Data Index: 3179488 (Open Web Text)

Max Activating Token Index: 657

Text #8

Max Range: 4.8606. Min Range: -4.8606

Max Act: 4.8320. Min Act: -0.1700

Data Index: 6116009 (Open Web Text)

Max Activating Token Index: 132

Text #9

Max Range: 4.8606. Min Range: -4.8606

Max Act: 4.8024. Min Act: -0.1700

Data Index: 1623556 (Open Web Text)

Max Activating Token Index: 642

Text #10

Max Range: 4.8606. Min Range: -4.8606

Max Act: 4.7914. Min Act: -0.1700

Data Index: 343453 (Open Web Text)

Max Activating Token Index: 612

Text #11

Max Range: 4.8606. Min Range: -4.8606

Max Act: 4.7725. Min Act: -0.1700

Data Index: 587585 (Open Web Text)

Max Activating Token Index: 497

Text #12

Max Range: 4.8606. Min Range: -4.8606

Max Act: 4.7707. Min Act: -0.1700

Data Index: 7456551 (Open Web Text)

Max Activating Token Index: 529

Text #13

Max Range: 4.8606. Min Range: -4.8606

Max Act: 4.7734. Min Act: -0.1700

Data Index: 1703431 (Open Web Text)

Max Activating Token Index: 284

Text #14

Max Range: 4.8606. Min Range: -4.8606

Max Act: 4.7520. Min Act: -0.1700

Data Index: 8159742 (Open Web Text)

Max Activating Token Index: 733

Text #15

Max Range: 4.8606. Min Range: -4.8606

Max Act: 4.7866. Min Act: -0.1700

Data Index: 6798952 (Open Web Text)

Max Activating Token Index: 654

Text #16

Max Range: 4.8606. Min Range: -4.8606

Max Act: 4.7697. Min Act: -0.1700

Data Index: 8705023 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 4.8606. Min Range: -4.8606

Max Act: 4.7397. Min Act: -0.1700

Data Index: 704470 (Open Web Text)

Max Activating Token Index: 393

Text #18

Max Range: 4.8606. Min Range: -4.8606

Max Act: 4.7666. Min Act: -0.1700

Data Index: 6701388 (Open Web Text)

Max Activating Token Index: 559

Text #19

Max Range: 4.8606. Min Range: -4.8606

Max Act: 4.7427. Min Act: -0.1700

Data Index: 905641 (Open Web Text)

Max Activating Token Index: 545