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

Dataset: Open Web Text

Neuron 724 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: 5.6762. Min Range: -5.6762

Max Act: 5.6762. Min Act: -0.1700

Data Index: 5004527 (Open Web Text)

Max Activating Token Index: 658

Text #1

Max Range: 5.6762. Min Range: -5.6762

Max Act: 5.5752. Min Act: -0.1700

Data Index: 2772910 (Open Web Text)

Max Activating Token Index: 625

Text #2

Max Range: 5.6762. Min Range: -5.6762

Max Act: 5.5788. Min Act: -0.1700

Data Index: 4009372 (Open Web Text)

Max Activating Token Index: 616

Text #3

Max Range: 5.6762. Min Range: -5.6762

Max Act: 5.5766. Min Act: -0.1700

Data Index: 3071229 (Open Web Text)

Max Activating Token Index: 609

Text #4

Max Range: 5.6762. Min Range: -5.6762

Max Act: 5.5494. Min Act: -0.1700

Data Index: 6094838 (Open Web Text)

Max Activating Token Index: 118

Text #5

Max Range: 5.6762. Min Range: -5.6762

Max Act: 5.5269. Min Act: -0.1700

Data Index: 3374670 (Open Web Text)

Max Activating Token Index: 242

Text #6

Max Range: 5.6762. Min Range: -5.6762

Max Act: 5.5139. Min Act: -0.1700

Data Index: 8255698 (Open Web Text)

Max Activating Token Index: 676

Text #7

Max Range: 5.6762. Min Range: -5.6762

Max Act: 5.4702. Min Act: -0.1700

Data Index: 8725147 (Open Web Text)

Max Activating Token Index: 577

Text #8

Max Range: 5.6762. Min Range: -5.6762

Max Act: 5.4269. Min Act: -0.1700

Data Index: 1861392 (Open Web Text)

Max Activating Token Index: 445

Text #9

Max Range: 5.6762. Min Range: -5.6762

Max Act: 5.4474. Min Act: -0.1700

Data Index: 7911847 (Open Web Text)

Max Activating Token Index: 354

Text #10

Max Range: 5.6762. Min Range: -5.6762

Max Act: 5.4277. Min Act: -0.1700

Data Index: 4992126 (Open Web Text)

Max Activating Token Index: 323

Text #11

Max Range: 5.6762. Min Range: -5.6762

Max Act: 5.4389. Min Act: -0.1700

Data Index: 6093734 (Open Web Text)

Max Activating Token Index: 446

Text #12

Max Range: 5.6762. Min Range: -5.6762

Max Act: 5.4365. Min Act: -0.1700

Data Index: 4281181 (Open Web Text)

Max Activating Token Index: 327

Text #13

Max Range: 5.6762. Min Range: -5.6762

Max Act: 5.4068. Min Act: -0.1700

Data Index: 5149566 (Open Web Text)

Max Activating Token Index: 681

Text #14

Max Range: 5.6762. Min Range: -5.6762

Max Act: 5.3588. Min Act: -0.1700

Data Index: 6951425 (Open Web Text)

Max Activating Token Index: 681

Text #15

Max Range: 5.6762. Min Range: -5.6762

Max Act: 5.3938. Min Act: -0.1700

Data Index: 8450956 (Open Web Text)

Max Activating Token Index: 769

Text #16

Max Range: 5.6762. Min Range: -5.6762

Max Act: 5.3744. Min Act: -0.1700

Data Index: 2288233 (Open Web Text)

Max Activating Token Index: 39

Text #17

Max Range: 5.6762. Min Range: -5.6762

Max Act: 5.3739. Min Act: -0.1700

Data Index: 8808239 (Open Web Text)

Max Activating Token Index: 517

Text #18

Max Range: 5.6762. Min Range: -5.6762

Max Act: 5.3851. Min Act: -0.1700

Data Index: 2580543 (Open Web Text)

Max Activating Token Index: 660

Text #19

Max Range: 5.6762. Min Range: -5.6762

Max Act: 5.3828. Min Act: -0.1700

Data Index: 2453584 (Open Web Text)

Max Activating Token Index: 361