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

Dataset: Open Web Text

Neuron 2455 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: 3.1605. Min Range: -3.1605

Max Act: 3.1605. Min Act: -0.1700

Data Index: 1979786 (Open Web Text)

Max Activating Token Index: 531

Text #1

Max Range: 3.1605. Min Range: -3.1605

Max Act: 3.1080. Min Act: -0.1700

Data Index: 2682803 (Open Web Text)

Max Activating Token Index: 793

Text #2

Max Range: 3.1605. Min Range: -3.1605

Max Act: 3.1012. Min Act: -0.1700

Data Index: 8247757 (Open Web Text)

Max Activating Token Index: 9

Text #3

Max Range: 3.1605. Min Range: -3.1605

Max Act: 3.0783. Min Act: -0.1700

Data Index: 326361 (Open Web Text)

Max Activating Token Index: 383

Text #4

Max Range: 3.1605. Min Range: -3.1605

Max Act: 3.0440. Min Act: -0.1700

Data Index: 2635577 (Open Web Text)

Max Activating Token Index: 868

Text #5

Max Range: 3.1605. Min Range: -3.1605

Max Act: 3.0114. Min Act: -0.1700

Data Index: 4125376 (Open Web Text)

Max Activating Token Index: 915

Text #6

Max Range: 3.1605. Min Range: -3.1605

Max Act: 3.0168. Min Act: -0.1700

Data Index: 2624808 (Open Web Text)

Max Activating Token Index: 139

Text #7

Max Range: 3.1605. Min Range: -3.1605

Max Act: 2.9797. Min Act: -0.1700

Data Index: 6542510 (Open Web Text)

Max Activating Token Index: 682

Text #8

Max Range: 3.1605. Min Range: -3.1605

Max Act: 2.9915. Min Act: -0.1700

Data Index: 1068798 (Open Web Text)

Max Activating Token Index: 575

Text #9

Max Range: 3.1605. Min Range: -3.1605

Max Act: 2.9944. Min Act: -0.1700

Data Index: 75915 (Open Web Text)

Max Activating Token Index: 74

Text #10

Max Range: 3.1605. Min Range: -3.1605

Max Act: 2.9551. Min Act: -0.1700

Data Index: 1243484 (Open Web Text)

Max Activating Token Index: 594

Text #11

Max Range: 3.1605. Min Range: -3.1605

Max Act: 2.9378. Min Act: -0.1700

Data Index: 479966 (Open Web Text)

Max Activating Token Index: 640

Text #12

Max Range: 3.1605. Min Range: -3.1605

Max Act: 2.9285. Min Act: -0.1700

Data Index: 6266007 (Open Web Text)

Max Activating Token Index: 193

Text #13

Max Range: 3.1605. Min Range: -3.1605

Max Act: 2.9068. Min Act: -0.1700

Data Index: 3233189 (Open Web Text)

Max Activating Token Index: 363

Text #14

Max Range: 3.1605. Min Range: -3.1605

Max Act: 2.9176. Min Act: -0.1700

Data Index: 4826568 (Open Web Text)

Max Activating Token Index: 508

Text #15

Max Range: 3.1605. Min Range: -3.1605

Max Act: 2.9500. Min Act: -0.1700

Data Index: 4604570 (Open Web Text)

Max Activating Token Index: 433

Text #16

Max Range: 3.1605. Min Range: -3.1605

Max Act: 2.9289. Min Act: -0.1700

Data Index: 6427266 (Open Web Text)

Max Activating Token Index: 751

Text #17

Max Range: 3.1605. Min Range: -3.1605

Max Act: 2.8988. Min Act: -0.1700

Data Index: 2839004 (Open Web Text)

Max Activating Token Index: 632

Text #18

Max Range: 3.1605. Min Range: -3.1605

Max Act: 2.9271. Min Act: -0.1700

Data Index: 1124086 (Open Web Text)

Max Activating Token Index: 954

Text #19

Max Range: 3.1605. Min Range: -3.1605

Max Act: 2.8918. Min Act: -0.1700

Data Index: 2921790 (Open Web Text)

Max Activating Token Index: 432