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

Dataset: Open Web Text

Neuron 2460 in Layer 3

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: 3.3844. Min Range: -3.3844

Max Act: 3.3844. Min Act: -0.1700

Data Index: 5799979 (Open Web Text)

Max Activating Token Index: 565

Text #1

Max Range: 3.3844. Min Range: -3.3844

Max Act: 3.3457. Min Act: -0.1700

Data Index: 7769366 (Open Web Text)

Max Activating Token Index: 257

Text #2

Max Range: 3.3844. Min Range: -3.3844

Max Act: 3.2941. Min Act: -0.1700

Data Index: 3212810 (Open Web Text)

Max Activating Token Index: 507

Text #3

Max Range: 3.3844. Min Range: -3.3844

Max Act: 3.2762. Min Act: -0.1700

Data Index: 4475366 (Open Web Text)

Max Activating Token Index: 675

Text #4

Max Range: 3.3844. Min Range: -3.3844

Max Act: 3.2823. Min Act: -0.1700

Data Index: 934500 (Open Web Text)

Max Activating Token Index: 836

Text #5

Max Range: 3.3844. Min Range: -3.3844

Max Act: 3.2902. Min Act: -0.1700

Data Index: 3290517 (Open Web Text)

Max Activating Token Index: 466

Text #6

Max Range: 3.3844. Min Range: -3.3844

Max Act: 3.2773. Min Act: -0.1700

Data Index: 836085 (Open Web Text)

Max Activating Token Index: 935

Text #7

Max Range: 3.3844. Min Range: -3.3844

Max Act: 3.2728. Min Act: -0.1700

Data Index: 2700121 (Open Web Text)

Max Activating Token Index: 624

Text #8

Max Range: 3.3844. Min Range: -3.3844

Max Act: 3.2800. Min Act: -0.1700

Data Index: 2622096 (Open Web Text)

Max Activating Token Index: 551

Text #9

Max Range: 3.3844. Min Range: -3.3844

Max Act: 3.2573. Min Act: -0.1700

Data Index: 4260881 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 3.3844. Min Range: -3.3844

Max Act: 3.2701. Min Act: -0.1700

Data Index: 8517772 (Open Web Text)

Max Activating Token Index: 954

Text #11

Max Range: 3.3844. Min Range: -3.3844

Max Act: 3.2686. Min Act: -0.1700

Data Index: 6488173 (Open Web Text)

Max Activating Token Index: 48

Text #12

Max Range: 3.3844. Min Range: -3.3844

Max Act: 3.2608. Min Act: -0.1700

Data Index: 7115746 (Open Web Text)

Max Activating Token Index: 688

Text #13

Max Range: 3.3844. Min Range: -3.3844

Max Act: 3.2387. Min Act: -0.1700

Data Index: 1866202 (Open Web Text)

Max Activating Token Index: 276

Text #14

Max Range: 3.3844. Min Range: -3.3844

Max Act: 3.2315. Min Act: -0.1700

Data Index: 8637887 (Open Web Text)

Max Activating Token Index: 801

Text #15

Max Range: 3.3844. Min Range: -3.3844

Max Act: 3.2545. Min Act: -0.1700

Data Index: 6793633 (Open Web Text)

Max Activating Token Index: 283

Text #16

Max Range: 3.3844. Min Range: -3.3844

Max Act: 3.2422. Min Act: -0.1700

Data Index: 6430407 (Open Web Text)

Max Activating Token Index: 737

Text #17

Max Range: 3.3844. Min Range: -3.3844

Max Act: 3.2425. Min Act: -0.1700

Data Index: 4947116 (Open Web Text)

Max Activating Token Index: 213

Text #18

Max Range: 3.3844. Min Range: -3.3844

Max Act: 3.2596. Min Act: -0.1700

Data Index: 5052560 (Open Web Text)

Max Activating Token Index: 167

Text #19

Max Range: 3.3844. Min Range: -3.3844

Max Act: 3.2553. Min Act: -0.1700

Data Index: 4990934 (Open Web Text)

Max Activating Token Index: 766