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

Dataset: Open Web Text

Neuron 478 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: 6.9338. Min Range: -6.9338

Max Act: 6.9338. Min Act: -0.1700

Data Index: 4388882 (Open Web Text)

Max Activating Token Index: 707

Text #1

Max Range: 6.9338. Min Range: -6.9338

Max Act: 6.5904. Min Act: -0.1700

Data Index: 1482758 (Open Web Text)

Max Activating Token Index: 315

Text #2

Max Range: 6.9338. Min Range: -6.9338

Max Act: 6.5651. Min Act: -0.1700

Data Index: 6292929 (Open Web Text)

Max Activating Token Index: 54

Text #3

Max Range: 6.9338. Min Range: -6.9338

Max Act: 6.4594. Min Act: -0.1700

Data Index: 4347221 (Open Web Text)

Max Activating Token Index: 723

Text #4

Max Range: 6.9338. Min Range: -6.9338

Max Act: 6.4427. Min Act: -0.1700

Data Index: 936736 (Open Web Text)

Max Activating Token Index: 886

Text #5

Max Range: 6.9338. Min Range: -6.9338

Max Act: 6.3948. Min Act: -0.1700

Data Index: 2747833 (Open Web Text)

Max Activating Token Index: 567

Text #6

Max Range: 6.9338. Min Range: -6.9338

Max Act: 6.3714. Min Act: -0.1700

Data Index: 3562089 (Open Web Text)

Max Activating Token Index: 617

Text #7

Max Range: 6.9338. Min Range: -6.9338

Max Act: 6.3466. Min Act: -0.1700

Data Index: 3883138 (Open Web Text)

Max Activating Token Index: 702

Text #8

Max Range: 6.9338. Min Range: -6.9338

Max Act: 6.2826. Min Act: -0.1700

Data Index: 1680325 (Open Web Text)

Max Activating Token Index: 656

Text #9

Max Range: 6.9338. Min Range: -6.9338

Max Act: 6.3193. Min Act: -0.1700

Data Index: 3969508 (Open Web Text)

Max Activating Token Index: 24

Text #10

Max Range: 6.9338. Min Range: -6.9338

Max Act: 6.3198. Min Act: -0.1700

Data Index: 1408744 (Open Web Text)

Max Activating Token Index: 152

Text #11

Max Range: 6.9338. Min Range: -6.9338

Max Act: 6.2910. Min Act: -0.1700

Data Index: 2534759 (Open Web Text)

Max Activating Token Index: 39

Text #12

Max Range: 6.9338. Min Range: -6.9338

Max Act: 6.2648. Min Act: -0.1700

Data Index: 6766939 (Open Web Text)

Max Activating Token Index: 549

Text #13

Max Range: 6.9338. Min Range: -6.9338

Max Act: 6.3357. Min Act: -0.1700

Data Index: 2670211 (Open Web Text)

Max Activating Token Index: 701

Text #14

Max Range: 6.9338. Min Range: -6.9338

Max Act: 6.2581. Min Act: -0.1700

Data Index: 6568531 (Open Web Text)

Max Activating Token Index: 943

Text #15

Max Range: 6.9338. Min Range: -6.9338

Max Act: 6.2770. Min Act: -0.1700

Data Index: 7894053 (Open Web Text)

Max Activating Token Index: 740

Text #16

Max Range: 6.9338. Min Range: -6.9338

Max Act: 6.2355. Min Act: -0.1700

Data Index: 8629475 (Open Web Text)

Max Activating Token Index: 821

Text #17

Max Range: 6.9338. Min Range: -6.9338

Max Act: 6.1948. Min Act: -0.1700

Data Index: 3765402 (Open Web Text)

Max Activating Token Index: 290

Text #18

Max Range: 6.9338. Min Range: -6.9338

Max Act: 6.1813. Min Act: -0.1700

Data Index: 2993981 (Open Web Text)

Max Activating Token Index: 868

Text #19

Max Range: 6.9338. Min Range: -6.9338

Max Act: 6.1282. Min Act: -0.1700

Data Index: 6567272 (Open Web Text)

Max Activating Token Index: 449