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

Dataset: Open Web Text

Neuron 167 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: 6.0817. Min Range: -6.0817

Max Act: 6.0817. Min Act: -0.1700

Data Index: 3363059 (Open Web Text)

Max Activating Token Index: 461

Text #1

Max Range: 6.0817. Min Range: -6.0817

Max Act: 5.9052. Min Act: -0.1700

Data Index: 7174721 (Open Web Text)

Max Activating Token Index: 133

Text #2

Max Range: 6.0817. Min Range: -6.0817

Max Act: 5.7625. Min Act: -0.1700

Data Index: 8332737 (Open Web Text)

Max Activating Token Index: 688

Text #3

Max Range: 6.0817. Min Range: -6.0817

Max Act: 5.7082. Min Act: -0.1700

Data Index: 6883841 (Open Web Text)

Max Activating Token Index: 466

Text #4

Max Range: 6.0817. Min Range: -6.0817

Max Act: 5.6211. Min Act: -0.1700

Data Index: 1131590 (Open Web Text)

Max Activating Token Index: 807

Text #5

Max Range: 6.0817. Min Range: -6.0817

Max Act: 5.6517. Min Act: -0.1700

Data Index: 2596621 (Open Web Text)

Max Activating Token Index: 344

Text #6

Max Range: 6.0817. Min Range: -6.0817

Max Act: 5.6084. Min Act: -0.1700

Data Index: 7550404 (Open Web Text)

Max Activating Token Index: 77

Text #7

Max Range: 6.0817. Min Range: -6.0817

Max Act: 5.6247. Min Act: -0.1700

Data Index: 638340 (Open Web Text)

Max Activating Token Index: 835

Text #8

Max Range: 6.0817. Min Range: -6.0817

Max Act: 5.4985. Min Act: -0.1700

Data Index: 6492844 (Open Web Text)

Max Activating Token Index: 402

Text #9

Max Range: 6.0817. Min Range: -6.0817

Max Act: 5.4600. Min Act: -0.1700

Data Index: 4296221 (Open Web Text)

Max Activating Token Index: 766

Text #10

Max Range: 6.0817. Min Range: -6.0817

Max Act: 5.4393. Min Act: -0.1700

Data Index: 4000465 (Open Web Text)

Max Activating Token Index: 581

Text #11

Max Range: 6.0817. Min Range: -6.0817

Max Act: 5.4604. Min Act: -0.1700

Data Index: 8105546 (Open Web Text)

Max Activating Token Index: 146

Text #12

Max Range: 6.0817. Min Range: -6.0817

Max Act: 5.4511. Min Act: -0.1700

Data Index: 2701306 (Open Web Text)

Max Activating Token Index: 159

Text #13

Max Range: 6.0817. Min Range: -6.0817

Max Act: 5.4385. Min Act: -0.1700

Data Index: 3554931 (Open Web Text)

Max Activating Token Index: 488

Text #14

Max Range: 6.0817. Min Range: -6.0817

Max Act: 5.3942. Min Act: -0.1700

Data Index: 8390701 (Open Web Text)

Max Activating Token Index: 616

Text #15

Max Range: 6.0817. Min Range: -6.0817

Max Act: 5.3836. Min Act: -0.1700

Data Index: 1236777 (Open Web Text)

Max Activating Token Index: 186

Text #16

Max Range: 6.0817. Min Range: -6.0817

Max Act: 5.4560. Min Act: -0.1700

Data Index: 865205 (Open Web Text)

Max Activating Token Index: 620

Text #17

Max Range: 6.0817. Min Range: -6.0817

Max Act: 5.4101. Min Act: -0.1700

Data Index: 8143826 (Open Web Text)

Max Activating Token Index: 420

Text #18

Max Range: 6.0817. Min Range: -6.0817

Max Act: 5.3694. Min Act: -0.1700

Data Index: 5289551 (Open Web Text)

Max Activating Token Index: 722

Text #19

Max Range: 6.0817. Min Range: -6.0817

Max Act: 5.4436. Min Act: -0.1700

Data Index: 6039332 (Open Web Text)

Max Activating Token Index: 431