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

Dataset: Open Web Text

Neuron 2820 in Layer 4

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: 2.3685. Min Range: -2.3685

Max Act: 2.3623. Min Act: -0.1700

Data Index: 4556085 (Open Web Text)

Max Activating Token Index: 967

Text #1

Max Range: 2.3685. Min Range: -2.3685

Max Act: 2.3685. Min Act: -0.1700

Data Index: 5711389 (Open Web Text)

Max Activating Token Index: 394

Text #2

Max Range: 2.3685. Min Range: -2.3685

Max Act: 2.3269. Min Act: -0.1700

Data Index: 2553212 (Open Web Text)

Max Activating Token Index: 689

Text #3

Max Range: 2.3685. Min Range: -2.3685

Max Act: 2.3130. Min Act: -0.1700

Data Index: 4133431 (Open Web Text)

Max Activating Token Index: 150

Text #4

Max Range: 2.3685. Min Range: -2.3685

Max Act: 2.3078. Min Act: -0.1700

Data Index: 1978930 (Open Web Text)

Max Activating Token Index: 881

Text #5

Max Range: 2.3685. Min Range: -2.3685

Max Act: 2.3048. Min Act: -0.1700

Data Index: 1791429 (Open Web Text)

Max Activating Token Index: 480

Text #6

Max Range: 2.3685. Min Range: -2.3685

Max Act: 2.2763. Min Act: -0.1700

Data Index: 8810125 (Open Web Text)

Max Activating Token Index: 188

Text #7

Max Range: 2.3685. Min Range: -2.3685

Max Act: 2.2734. Min Act: -0.1700

Data Index: 2826187 (Open Web Text)

Max Activating Token Index: 744

Text #8

Max Range: 2.3685. Min Range: -2.3685

Max Act: 2.2579. Min Act: -0.1700

Data Index: 3429405 (Open Web Text)

Max Activating Token Index: 777

Text #9

Max Range: 2.3685. Min Range: -2.3685

Max Act: 2.2625. Min Act: -0.1700

Data Index: 5709763 (Open Web Text)

Max Activating Token Index: 744

Text #10

Max Range: 2.3685. Min Range: -2.3685

Max Act: 2.2563. Min Act: -0.1700

Data Index: 53625 (Open Web Text)

Max Activating Token Index: 762

Text #11

Max Range: 2.3685. Min Range: -2.3685

Max Act: 2.2442. Min Act: -0.1700

Data Index: 8283013 (Open Web Text)

Max Activating Token Index: 377

Text #12

Max Range: 2.3685. Min Range: -2.3685

Max Act: 2.2356. Min Act: -0.1700

Data Index: 5724046 (Open Web Text)

Max Activating Token Index: 937

Text #13

Max Range: 2.3685. Min Range: -2.3685

Max Act: 2.2508. Min Act: -0.1700

Data Index: 1617688 (Open Web Text)

Max Activating Token Index: 294

Text #14

Max Range: 2.3685. Min Range: -2.3685

Max Act: 2.2559. Min Act: -0.1700

Data Index: 7400828 (Open Web Text)

Max Activating Token Index: 249

Text #15

Max Range: 2.3685. Min Range: -2.3685

Max Act: 2.2594. Min Act: -0.1700

Data Index: 5735423 (Open Web Text)

Max Activating Token Index: 415

Text #16

Max Range: 2.3685. Min Range: -2.3685

Max Act: 2.2286. Min Act: -0.1700

Data Index: 1138135 (Open Web Text)

Max Activating Token Index: 786

Text #17

Max Range: 2.3685. Min Range: -2.3685

Max Act: 2.2286. Min Act: -0.1700

Data Index: 5632180 (Open Web Text)

Max Activating Token Index: 564

Text #18

Max Range: 2.3685. Min Range: -2.3685

Max Act: 2.2246. Min Act: -0.1700

Data Index: 4218849 (Open Web Text)

Max Activating Token Index: 368

Text #19

Max Range: 2.3685. Min Range: -2.3685

Max Act: 2.2265. Min Act: -0.1700

Data Index: 6262442 (Open Web Text)

Max Activating Token Index: 1020