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

Dataset: Open Web Text

Neuron 1229 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: 4.3755. Min Range: -4.3755

Max Act: 4.3755. Min Act: -0.1700

Data Index: 6808180 (Open Web Text)

Max Activating Token Index: 1016

Text #1

Max Range: 4.3755. Min Range: -4.3755

Max Act: 4.2703. Min Act: -0.1700

Data Index: 1528802 (Open Web Text)

Max Activating Token Index: 94

Text #2

Max Range: 4.3755. Min Range: -4.3755

Max Act: 4.2274. Min Act: -0.1700

Data Index: 3222237 (Open Web Text)

Max Activating Token Index: 580

Text #3

Max Range: 4.3755. Min Range: -4.3755

Max Act: 4.1977. Min Act: -0.1700

Data Index: 7937043 (Open Web Text)

Max Activating Token Index: 272

Text #4

Max Range: 4.3755. Min Range: -4.3755

Max Act: 4.2088. Min Act: -0.1700

Data Index: 6691625 (Open Web Text)

Max Activating Token Index: 843

Text #5

Max Range: 4.3755. Min Range: -4.3755

Max Act: 4.1282. Min Act: -0.1700

Data Index: 8408286 (Open Web Text)

Max Activating Token Index: 342

Text #6

Max Range: 4.3755. Min Range: -4.3755

Max Act: 4.1514. Min Act: -0.1700

Data Index: 4292789 (Open Web Text)

Max Activating Token Index: 339

Text #7

Max Range: 4.3755. Min Range: -4.3755

Max Act: 4.1142. Min Act: -0.1700

Data Index: 947002 (Open Web Text)

Max Activating Token Index: 281

Text #8

Max Range: 4.3755. Min Range: -4.3755

Max Act: 4.0847. Min Act: -0.1700

Data Index: 3856501 (Open Web Text)

Max Activating Token Index: 714

Text #9

Max Range: 4.3755. Min Range: -4.3755

Max Act: 4.0842. Min Act: -0.1700

Data Index: 1702307 (Open Web Text)

Max Activating Token Index: 411

Text #10

Max Range: 4.3755. Min Range: -4.3755

Max Act: 4.0730. Min Act: -0.1700

Data Index: 4845511 (Open Web Text)

Max Activating Token Index: 867

Text #11

Max Range: 4.3755. Min Range: -4.3755

Max Act: 4.0525. Min Act: -0.1700

Data Index: 7914759 (Open Web Text)

Max Activating Token Index: 595

Text #12

Max Range: 4.3755. Min Range: -4.3755

Max Act: 4.0757. Min Act: -0.1700

Data Index: 8616649 (Open Web Text)

Max Activating Token Index: 841

Text #13

Max Range: 4.3755. Min Range: -4.3755

Max Act: 4.0755. Min Act: -0.1700

Data Index: 8702156 (Open Web Text)

Max Activating Token Index: 460

Text #14

Max Range: 4.3755. Min Range: -4.3755

Max Act: 4.0807. Min Act: -0.1700

Data Index: 3752106 (Open Web Text)

Max Activating Token Index: 426

Text #15

Max Range: 4.3755. Min Range: -4.3755

Max Act: 4.0790. Min Act: -0.1700

Data Index: 7261592 (Open Web Text)

Max Activating Token Index: 846

Text #16

Max Range: 4.3755. Min Range: -4.3755

Max Act: 4.0475. Min Act: -0.1700

Data Index: 6780818 (Open Web Text)

Max Activating Token Index: 82

Text #17

Max Range: 4.3755. Min Range: -4.3755

Max Act: 4.0472. Min Act: -0.1700

Data Index: 966578 (Open Web Text)

Max Activating Token Index: 478

Text #18

Max Range: 4.3755. Min Range: -4.3755

Max Act: 4.0383. Min Act: -0.1700

Data Index: 2422981 (Open Web Text)

Max Activating Token Index: 983

Text #19

Max Range: 4.3755. Min Range: -4.3755

Max Act: 4.0491. Min Act: -0.1700

Data Index: 6954871 (Open Web Text)

Max Activating Token Index: 832