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

Dataset: Open Web Text

Neuron 2662 in Layer 6

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: 7.5731. Min Range: -7.5731

Max Act: 7.5731. Min Act: -0.1700

Data Index: 2585358 (Open Web Text)

Max Activating Token Index: 849

Text #1

Max Range: 7.5731. Min Range: -7.5731

Max Act: 7.4158. Min Act: -0.1700

Data Index: 5745764 (Open Web Text)

Max Activating Token Index: 732

Text #2

Max Range: 7.5731. Min Range: -7.5731

Max Act: 7.3645. Min Act: -0.1700

Data Index: 4314369 (Open Web Text)

Max Activating Token Index: 993

Text #3

Max Range: 7.5731. Min Range: -7.5731

Max Act: 7.3716. Min Act: -0.1700

Data Index: 2585359 (Open Web Text)

Max Activating Token Index: 983

Text #4

Max Range: 7.5731. Min Range: -7.5731

Max Act: 7.3051. Min Act: -0.1700

Data Index: 1596195 (Open Web Text)

Max Activating Token Index: 428

Text #5

Max Range: 7.5731. Min Range: -7.5731

Max Act: 7.3422. Min Act: -0.1700

Data Index: 1109506 (Open Web Text)

Max Activating Token Index: 33

Text #6

Max Range: 7.5731. Min Range: -7.5731

Max Act: 7.2908. Min Act: -0.1700

Data Index: 620338 (Open Web Text)

Max Activating Token Index: 200

Text #7

Max Range: 7.5731. Min Range: -7.5731

Max Act: 7.2061. Min Act: -0.1700

Data Index: 2105041 (Open Web Text)

Max Activating Token Index: 1014

Text #8

Max Range: 7.5731. Min Range: -7.5731

Max Act: 7.2279. Min Act: -0.1700

Data Index: 6524228 (Open Web Text)

Max Activating Token Index: 715

Text #9

Max Range: 7.5731. Min Range: -7.5731

Max Act: 7.1729. Min Act: -0.1700

Data Index: 7802953 (Open Web Text)

Max Activating Token Index: 297

Text #10

Max Range: 7.5731. Min Range: -7.5731

Max Act: 7.1650. Min Act: -0.1700

Data Index: 4844549 (Open Web Text)

Max Activating Token Index: 966

Text #11

Max Range: 7.5731. Min Range: -7.5731

Max Act: 7.1769. Min Act: -0.1700

Data Index: 5123603 (Open Web Text)

Max Activating Token Index: 905

Text #12

Max Range: 7.5731. Min Range: -7.5731

Max Act: 7.1283. Min Act: -0.1700

Data Index: 6127007 (Open Web Text)

Max Activating Token Index: 983

Text #13

Max Range: 7.5731. Min Range: -7.5731

Max Act: 7.2041. Min Act: -0.1700

Data Index: 5558577 (Open Web Text)

Max Activating Token Index: 554

Text #14

Max Range: 7.5731. Min Range: -7.5731

Max Act: 7.1866. Min Act: -0.1700

Data Index: 1761687 (Open Web Text)

Max Activating Token Index: 596

Text #15

Max Range: 7.5731. Min Range: -7.5731

Max Act: 7.1566. Min Act: -0.1700

Data Index: 496904 (Open Web Text)

Max Activating Token Index: 954

Text #16

Max Range: 7.5731. Min Range: -7.5731

Max Act: 7.1683. Min Act: -0.1700

Data Index: 1317237 (Open Web Text)

Max Activating Token Index: 502

Text #17

Max Range: 7.5731. Min Range: -7.5731

Max Act: 7.1391. Min Act: -0.1700

Data Index: 6521647 (Open Web Text)

Max Activating Token Index: 251

Text #18

Max Range: 7.5731. Min Range: -7.5731

Max Act: 7.1081. Min Act: -0.1700

Data Index: 2439509 (Open Web Text)

Max Activating Token Index: 833

Text #19

Max Range: 7.5731. Min Range: -7.5731

Max Act: 7.0936. Min Act: -0.1700

Data Index: 2709740 (Open Web Text)

Max Activating Token Index: 519