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

Dataset: Open Web Text

Neuron 2033 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: 1.7558. Min Range: -1.7558

Max Act: 1.7558. Min Act: -0.1700

Data Index: 2022264 (Open Web Text)

Max Activating Token Index: 481

Text #1

Max Range: 1.7558. Min Range: -1.7558

Max Act: 1.7481. Min Act: -0.1700

Data Index: 7946310 (Open Web Text)

Max Activating Token Index: 219

Text #2

Max Range: 1.7558. Min Range: -1.7558

Max Act: 1.7397. Min Act: -0.1700

Data Index: 4990235 (Open Web Text)

Max Activating Token Index: 632

Text #3

Max Range: 1.7558. Min Range: -1.7558

Max Act: 1.7115. Min Act: -0.1700

Data Index: 7744497 (Open Web Text)

Max Activating Token Index: 514

Text #4

Max Range: 1.7558. Min Range: -1.7558

Max Act: 1.7115. Min Act: -0.1700

Data Index: 2788758 (Open Web Text)

Max Activating Token Index: 309

Text #5

Max Range: 1.7558. Min Range: -1.7558

Max Act: 1.6997. Min Act: -0.1700

Data Index: 4960473 (Open Web Text)

Max Activating Token Index: 197

Text #6

Max Range: 1.7558. Min Range: -1.7558

Max Act: 1.6903. Min Act: -0.1688

Data Index: 435635 (Open Web Text)

Max Activating Token Index: 480

Text #7

Max Range: 1.7558. Min Range: -1.7558

Max Act: 1.6772. Min Act: -0.1700

Data Index: 1675865 (Open Web Text)

Max Activating Token Index: 426

Text #8

Max Range: 1.7558. Min Range: -1.7558

Max Act: 1.6814. Min Act: -0.1700

Data Index: 4930829 (Open Web Text)

Max Activating Token Index: 966

Text #9

Max Range: 1.7558. Min Range: -1.7558

Max Act: 1.6859. Min Act: -0.1700

Data Index: 5480797 (Open Web Text)

Max Activating Token Index: 476

Text #10

Max Range: 1.7558. Min Range: -1.7558

Max Act: 1.6884. Min Act: -0.1700

Data Index: 2416556 (Open Web Text)

Max Activating Token Index: 183

Text #11

Max Range: 1.7558. Min Range: -1.7558

Max Act: 1.6894. Min Act: -0.1700

Data Index: 751471 (Open Web Text)

Max Activating Token Index: 90

Text #12

Max Range: 1.7558. Min Range: -1.7558

Max Act: 1.6718. Min Act: -0.1700

Data Index: 3475155 (Open Web Text)

Max Activating Token Index: 618

Text #13

Max Range: 1.7558. Min Range: -1.7558

Max Act: 1.6744. Min Act: -0.1700

Data Index: 2537901 (Open Web Text)

Max Activating Token Index: 202

Text #14

Max Range: 1.7558. Min Range: -1.7558

Max Act: 1.6794. Min Act: -0.1700

Data Index: 1534432 (Open Web Text)

Max Activating Token Index: 649

Text #15

Max Range: 1.7558. Min Range: -1.7558

Max Act: 1.6690. Min Act: -0.1700

Data Index: 6190509 (Open Web Text)

Max Activating Token Index: 450

Text #16

Max Range: 1.7558. Min Range: -1.7558

Max Act: 1.6727. Min Act: -0.1700

Data Index: 785766 (Open Web Text)

Max Activating Token Index: 584

Text #17

Max Range: 1.7558. Min Range: -1.7558

Max Act: 1.6743. Min Act: -0.1700

Data Index: 6125632 (Open Web Text)

Max Activating Token Index: 310

Text #18

Max Range: 1.7558. Min Range: -1.7558

Max Act: 1.6754. Min Act: -0.1700

Data Index: 4017823 (Open Web Text)

Max Activating Token Index: 604

Text #19

Max Range: 1.7558. Min Range: -1.7558

Max Act: 1.6802. Min Act: -0.1700

Data Index: 630737 (Open Web Text)

Max Activating Token Index: 591