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

Dataset: Open Web Text

Neuron 817 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: 3.8690. Min Range: -3.8690

Max Act: 3.8629. Min Act: -0.1700

Data Index: 1708157 (Open Web Text)

Max Activating Token Index: 307

Text #1

Max Range: 3.8690. Min Range: -3.8690

Max Act: 3.8690. Min Act: -0.1700

Data Index: 243833 (Open Web Text)

Max Activating Token Index: 962

Text #2

Max Range: 3.8690. Min Range: -3.8690

Max Act: 3.8444. Min Act: -0.1700

Data Index: 7451610 (Open Web Text)

Max Activating Token Index: 613

Text #3

Max Range: 3.8690. Min Range: -3.8690

Max Act: 3.8255. Min Act: -0.1700

Data Index: 979058 (Open Web Text)

Max Activating Token Index: 590

Text #4

Max Range: 3.8690. Min Range: -3.8690

Max Act: 3.8472. Min Act: -0.1700

Data Index: 5428498 (Open Web Text)

Max Activating Token Index: 804

Text #5

Max Range: 3.8690. Min Range: -3.8690

Max Act: 3.7930. Min Act: -0.1700

Data Index: 6518785 (Open Web Text)

Max Activating Token Index: 604

Text #6

Max Range: 3.8690. Min Range: -3.8690

Max Act: 3.7890. Min Act: -0.1700

Data Index: 1519210 (Open Web Text)

Max Activating Token Index: 797

Text #7

Max Range: 3.8690. Min Range: -3.8690

Max Act: 3.7634. Min Act: -0.1700

Data Index: 4245521 (Open Web Text)

Max Activating Token Index: 551

Text #8

Max Range: 3.8690. Min Range: -3.8690

Max Act: 3.7847. Min Act: -0.1700

Data Index: 7713535 (Open Web Text)

Max Activating Token Index: 877

Text #9

Max Range: 3.8690. Min Range: -3.8690

Max Act: 3.7675. Min Act: -0.1700

Data Index: 3036127 (Open Web Text)

Max Activating Token Index: 34

Text #10

Max Range: 3.8690. Min Range: -3.8690

Max Act: 3.7668. Min Act: -0.1700

Data Index: 6012701 (Open Web Text)

Max Activating Token Index: 785

Text #11

Max Range: 3.8690. Min Range: -3.8690

Max Act: 3.7417. Min Act: -0.1700

Data Index: 8489148 (Open Web Text)

Max Activating Token Index: 674

Text #12

Max Range: 3.8690. Min Range: -3.8690

Max Act: 3.7622. Min Act: -0.1700

Data Index: 1821812 (Open Web Text)

Max Activating Token Index: 800

Text #13

Max Range: 3.8690. Min Range: -3.8690

Max Act: 3.7353. Min Act: -0.1700

Data Index: 933126 (Open Web Text)

Max Activating Token Index: 542

Text #14

Max Range: 3.8690. Min Range: -3.8690

Max Act: 3.7394. Min Act: -0.1700

Data Index: 8470065 (Open Web Text)

Max Activating Token Index: 656

Text #15

Max Range: 3.8690. Min Range: -3.8690

Max Act: 3.7242. Min Act: -0.1700

Data Index: 815105 (Open Web Text)

Max Activating Token Index: 933

Text #16

Max Range: 3.8690. Min Range: -3.8690

Max Act: 3.7484. Min Act: -0.1700

Data Index: 7870683 (Open Web Text)

Max Activating Token Index: 744

Text #17

Max Range: 3.8690. Min Range: -3.8690

Max Act: 3.7386. Min Act: -0.1700

Data Index: 5718163 (Open Web Text)

Max Activating Token Index: 94

Text #18

Max Range: 3.8690. Min Range: -3.8690

Max Act: 3.7061. Min Act: -0.1700

Data Index: 3031744 (Open Web Text)

Max Activating Token Index: 946

Text #19

Max Range: 3.8690. Min Range: -3.8690

Max Act: 3.7179. Min Act: -0.1700

Data Index: 1795926 (Open Web Text)

Max Activating Token Index: 740