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

Dataset: Open Web Text

Neuron 1646 in Layer 2

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: 3.0665. Min Range: -3.0665

Max Act: 3.0665. Min Act: -0.1700

Data Index: 3643706 (Open Web Text)

Max Activating Token Index: 344

Text #1

Max Range: 3.0665. Min Range: -3.0665

Max Act: 3.0126. Min Act: -0.1700

Data Index: 6512367 (Open Web Text)

Max Activating Token Index: 476

Text #2

Max Range: 3.0665. Min Range: -3.0665

Max Act: 3.0008. Min Act: -0.1700

Data Index: 7701001 (Open Web Text)

Max Activating Token Index: 399

Text #3

Max Range: 3.0665. Min Range: -3.0665

Max Act: 2.9595. Min Act: -0.1700

Data Index: 5552802 (Open Web Text)

Max Activating Token Index: 183

Text #4

Max Range: 3.0665. Min Range: -3.0665

Max Act: 2.9544. Min Act: -0.1700

Data Index: 1746813 (Open Web Text)

Max Activating Token Index: 120

Text #5

Max Range: 3.0665. Min Range: -3.0665

Max Act: 2.9546. Min Act: -0.1700

Data Index: 3512433 (Open Web Text)

Max Activating Token Index: 870

Text #6

Max Range: 3.0665. Min Range: -3.0665

Max Act: 2.9666. Min Act: -0.1700

Data Index: 6604219 (Open Web Text)

Max Activating Token Index: 762

Text #7

Max Range: 3.0665. Min Range: -3.0665

Max Act: 2.9576. Min Act: -0.1700

Data Index: 8793411 (Open Web Text)

Max Activating Token Index: 858

Text #8

Max Range: 3.0665. Min Range: -3.0665

Max Act: 2.9156. Min Act: -0.1700

Data Index: 4342559 (Open Web Text)

Max Activating Token Index: 676

Text #9

Max Range: 3.0665. Min Range: -3.0665

Max Act: 2.9051. Min Act: -0.1700

Data Index: 4109537 (Open Web Text)

Max Activating Token Index: 258

Text #10

Max Range: 3.0665. Min Range: -3.0665

Max Act: 2.8935. Min Act: -0.1700

Data Index: 1533961 (Open Web Text)

Max Activating Token Index: 1013

Text #11

Max Range: 3.0665. Min Range: -3.0665

Max Act: 2.8743. Min Act: -0.1700

Data Index: 66425 (Open Web Text)

Max Activating Token Index: 731

Text #12

Max Range: 3.0665. Min Range: -3.0665

Max Act: 2.9006. Min Act: -0.1700

Data Index: 3205051 (Open Web Text)

Max Activating Token Index: 894

Text #13

Max Range: 3.0665. Min Range: -3.0665

Max Act: 2.9122. Min Act: -0.1700

Data Index: 4030392 (Open Web Text)

Max Activating Token Index: 934

Text #14

Max Range: 3.0665. Min Range: -3.0665

Max Act: 2.8878. Min Act: -0.1700

Data Index: 3381319 (Open Web Text)

Max Activating Token Index: 1002

Text #15

Max Range: 3.0665. Min Range: -3.0665

Max Act: 2.8829. Min Act: -0.1700

Data Index: 1520544 (Open Web Text)

Max Activating Token Index: 802

Text #16

Max Range: 3.0665. Min Range: -3.0665

Max Act: 2.8844. Min Act: -0.1700

Data Index: 7307829 (Open Web Text)

Max Activating Token Index: 228

Text #17

Max Range: 3.0665. Min Range: -3.0665

Max Act: 2.8692. Min Act: -0.1700

Data Index: 8248005 (Open Web Text)

Max Activating Token Index: 136

Text #18

Max Range: 3.0665. Min Range: -3.0665

Max Act: 2.8637. Min Act: -0.1700

Data Index: 2316895 (Open Web Text)

Max Activating Token Index: 711

Text #19

Max Range: 3.0665. Min Range: -3.0665

Max Act: 2.8559. Min Act: -0.1700

Data Index: 1617899 (Open Web Text)

Max Activating Token Index: 345