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

Dataset: Open Web Text

Neuron 1866 in Layer 5

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: 1.4076. Min Range: -1.4076

Max Act: 1.4076. Min Act: -0.1699

Data Index: 3935439 (Open Web Text)

Max Activating Token Index: 388

Text #1

Max Range: 1.4076. Min Range: -1.4076

Max Act: 1.3354. Min Act: -0.1699

Data Index: 513121 (Open Web Text)

Max Activating Token Index: 568

Text #2

Max Range: 1.4076. Min Range: -1.4076

Max Act: 1.3201. Min Act: -0.1700

Data Index: 8002417 (Open Web Text)

Max Activating Token Index: 169

Text #3

Max Range: 1.4076. Min Range: -1.4076

Max Act: 1.2887. Min Act: -0.1699

Data Index: 2017000 (Open Web Text)

Max Activating Token Index: 668

Text #4

Max Range: 1.4076. Min Range: -1.4076

Max Act: 1.2738. Min Act: -0.1700

Data Index: 3888625 (Open Web Text)

Max Activating Token Index: 818

Text #5

Max Range: 1.4076. Min Range: -1.4076

Max Act: 1.2899. Min Act: -0.1700

Data Index: 7427809 (Open Web Text)

Max Activating Token Index: 995

Text #6

Max Range: 1.4076. Min Range: -1.4076

Max Act: 1.2675. Min Act: -0.1700

Data Index: 130595 (Open Web Text)

Max Activating Token Index: 283

Text #7

Max Range: 1.4076. Min Range: -1.4076

Max Act: 1.2703. Min Act: -0.1700

Data Index: 8806570 (Open Web Text)

Max Activating Token Index: 430

Text #8

Max Range: 1.4076. Min Range: -1.4076

Max Act: 1.2677. Min Act: -0.1699

Data Index: 8632553 (Open Web Text)

Max Activating Token Index: 395

Text #9

Max Range: 1.4076. Min Range: -1.4076

Max Act: 1.2602. Min Act: -0.1700

Data Index: 6944507 (Open Web Text)

Max Activating Token Index: 167

Text #10

Max Range: 1.4076. Min Range: -1.4076

Max Act: 1.2633. Min Act: -0.1700

Data Index: 2541693 (Open Web Text)

Max Activating Token Index: 779

Text #11

Max Range: 1.4076. Min Range: -1.4076

Max Act: 1.2702. Min Act: -0.1700

Data Index: 1634175 (Open Web Text)

Max Activating Token Index: 36

Text #12

Max Range: 1.4076. Min Range: -1.4076

Max Act: 1.2442. Min Act: -0.1700

Data Index: 2649550 (Open Web Text)

Max Activating Token Index: 601

Text #13

Max Range: 1.4076. Min Range: -1.4076

Max Act: 1.2726. Min Act: -0.1700

Data Index: 6043023 (Open Web Text)

Max Activating Token Index: 576

Text #14

Max Range: 1.4076. Min Range: -1.4076

Max Act: 1.2175. Min Act: -0.1700

Data Index: 1196563 (Open Web Text)

Max Activating Token Index: 582

Text #15

Max Range: 1.4076. Min Range: -1.4076

Max Act: 1.2557. Min Act: -0.1700

Data Index: 5664854 (Open Web Text)

Max Activating Token Index: 946

Text #16

Max Range: 1.4076. Min Range: -1.4076

Max Act: 1.2621. Min Act: -0.1700

Data Index: 3784112 (Open Web Text)

Max Activating Token Index: 450

Text #17

Max Range: 1.4076. Min Range: -1.4076

Max Act: 1.2629. Min Act: -0.1700

Data Index: 7595447 (Open Web Text)

Max Activating Token Index: 949

Text #18

Max Range: 1.4076. Min Range: -1.4076

Max Act: 1.2572. Min Act: -0.1700

Data Index: 2105585 (Open Web Text)

Max Activating Token Index: 133

Text #19

Max Range: 1.4076. Min Range: -1.4076

Max Act: 1.2490. Min Act: -0.1700

Data Index: 8676016 (Open Web Text)

Max Activating Token Index: 97