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

Dataset: Open Web Text

Neuron 1756 in Layer 3

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: 1.9950. Min Range: -1.9950

Max Act: 1.9950. Min Act: -0.1700

Data Index: 5582702 (Open Web Text)

Max Activating Token Index: 182

Text #1

Max Range: 1.9950. Min Range: -1.9950

Max Act: 1.9764. Min Act: -0.1700

Data Index: 6685170 (Open Web Text)

Max Activating Token Index: 371

Text #2

Max Range: 1.9950. Min Range: -1.9950

Max Act: 1.9615. Min Act: -0.1700

Data Index: 5927587 (Open Web Text)

Max Activating Token Index: 469

Text #3

Max Range: 1.9950. Min Range: -1.9950

Max Act: 1.9655. Min Act: -0.1700

Data Index: 7621077 (Open Web Text)

Max Activating Token Index: 605

Text #4

Max Range: 1.9950. Min Range: -1.9950

Max Act: 1.9679. Min Act: -0.1700

Data Index: 8588214 (Open Web Text)

Max Activating Token Index: 1012

Text #5

Max Range: 1.9950. Min Range: -1.9950

Max Act: 1.9396. Min Act: -0.1700

Data Index: 1492585 (Open Web Text)

Max Activating Token Index: 188

Text #6

Max Range: 1.9950. Min Range: -1.9950

Max Act: 1.9509. Min Act: -0.1700

Data Index: 3482694 (Open Web Text)

Max Activating Token Index: 247

Text #7

Max Range: 1.9950. Min Range: -1.9950

Max Act: 1.9463. Min Act: -0.1700

Data Index: 2335793 (Open Web Text)

Max Activating Token Index: 198

Text #8

Max Range: 1.9950. Min Range: -1.9950

Max Act: 1.9604. Min Act: -0.1700

Data Index: 8763318 (Open Web Text)

Max Activating Token Index: 46

Text #9

Max Range: 1.9950. Min Range: -1.9950

Max Act: 1.9550. Min Act: -0.1700

Data Index: 826363 (Open Web Text)

Max Activating Token Index: 870

Text #10

Max Range: 1.9950. Min Range: -1.9950

Max Act: 1.9516. Min Act: -0.1700

Data Index: 3914789 (Open Web Text)

Max Activating Token Index: 317

Text #11

Max Range: 1.9950. Min Range: -1.9950

Max Act: 1.9544. Min Act: -0.1700

Data Index: 7161558 (Open Web Text)

Max Activating Token Index: 410

Text #12

Max Range: 1.9950. Min Range: -1.9950

Max Act: 1.9263. Min Act: -0.1700

Data Index: 1022891 (Open Web Text)

Max Activating Token Index: 685

Text #13

Max Range: 1.9950. Min Range: -1.9950

Max Act: 1.9245. Min Act: -0.1700

Data Index: 6278199 (Open Web Text)

Max Activating Token Index: 274

Text #14

Max Range: 1.9950. Min Range: -1.9950

Max Act: 1.9352. Min Act: -0.1700

Data Index: 1225851 (Open Web Text)

Max Activating Token Index: 875

Text #15

Max Range: 1.9950. Min Range: -1.9950

Max Act: 1.9429. Min Act: -0.1700

Data Index: 3174029 (Open Web Text)

Max Activating Token Index: 509

Text #16

Max Range: 1.9950. Min Range: -1.9950

Max Act: 1.9255. Min Act: -0.1700

Data Index: 6062359 (Open Web Text)

Max Activating Token Index: 633

Text #17

Max Range: 1.9950. Min Range: -1.9950

Max Act: 1.9143. Min Act: -0.1700

Data Index: 2618825 (Open Web Text)

Max Activating Token Index: 633

Text #18

Max Range: 1.9950. Min Range: -1.9950

Max Act: 1.9133. Min Act: -0.1700

Data Index: 899306 (Open Web Text)

Max Activating Token Index: 226

Text #19

Max Range: 1.9950. Min Range: -1.9950

Max Act: 1.9105. Min Act: -0.1700

Data Index: 1680571 (Open Web Text)

Max Activating Token Index: 766