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

Dataset: Open Web Text

Neuron 433 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: 2.1538. Min Range: -2.1538

Max Act: 2.1383. Min Act: -0.1700

Data Index: 2841343 (Open Web Text)

Max Activating Token Index: 908

Text #1

Max Range: 2.1538. Min Range: -2.1538

Max Act: 2.1538. Min Act: -0.1700

Data Index: 7324256 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 2.1538. Min Range: -2.1538

Max Act: 2.1015. Min Act: -0.1700

Data Index: 6154389 (Open Web Text)

Max Activating Token Index: 63

Text #3

Max Range: 2.1538. Min Range: -2.1538

Max Act: 2.0897. Min Act: -0.1700

Data Index: 8421739 (Open Web Text)

Max Activating Token Index: 276

Text #4

Max Range: 2.1538. Min Range: -2.1538

Max Act: 2.0784. Min Act: -0.1700

Data Index: 3788338 (Open Web Text)

Max Activating Token Index: 722

Text #5

Max Range: 2.1538. Min Range: -2.1538

Max Act: 2.0238. Min Act: -0.1700

Data Index: 5940578 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 2.1538. Min Range: -2.1538

Max Act: 2.0295. Min Act: -0.1699

Data Index: 1355153 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 2.1538. Min Range: -2.1538

Max Act: 2.0287. Min Act: -0.1700

Data Index: 2074657 (Open Web Text)

Max Activating Token Index: 486

Text #8

Max Range: 2.1538. Min Range: -2.1538

Max Act: 2.0313. Min Act: -0.1700

Data Index: 8168739 (Open Web Text)

Max Activating Token Index: 896

Text #9

Max Range: 2.1538. Min Range: -2.1538

Max Act: 2.0261. Min Act: -0.1700

Data Index: 4647071 (Open Web Text)

Max Activating Token Index: 601

Text #10

Max Range: 2.1538. Min Range: -2.1538

Max Act: 1.9908. Min Act: -0.1700

Data Index: 17311 (Open Web Text)

Max Activating Token Index: 759

Text #11

Max Range: 2.1538. Min Range: -2.1538

Max Act: 2.0065. Min Act: -0.1700

Data Index: 1337727 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 2.1538. Min Range: -2.1538

Max Act: 1.9959. Min Act: -0.1700

Data Index: 7474656 (Open Web Text)

Max Activating Token Index: 1019

Text #13

Max Range: 2.1538. Min Range: -2.1538

Max Act: 1.9788. Min Act: -0.1700

Data Index: 1383289 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 2.1538. Min Range: -2.1538

Max Act: 1.9804. Min Act: -0.1700

Data Index: 138908 (Open Web Text)

Max Activating Token Index: 875

Text #15

Max Range: 2.1538. Min Range: -2.1538

Max Act: 1.9774. Min Act: -0.1700

Data Index: 437139 (Open Web Text)

Max Activating Token Index: 134

Text #16

Max Range: 2.1538. Min Range: -2.1538

Max Act: 1.9882. Min Act: -0.1700

Data Index: 1315351 (Open Web Text)

Max Activating Token Index: 431

Text #17

Max Range: 2.1538. Min Range: -2.1538

Max Act: 1.9833. Min Act: -0.1700

Data Index: 215373 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 2.1538. Min Range: -2.1538

Max Act: 1.9721. Min Act: -0.1700

Data Index: 5477907 (Open Web Text)

Max Activating Token Index: 498

Text #19

Max Range: 2.1538. Min Range: -2.1538

Max Act: 1.9878. Min Act: -0.1700

Data Index: 2751617 (Open Web Text)

Max Activating Token Index: 689