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

Dataset: Open Web Text

Neuron 1706 in Layer 5

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: 5.3398. Min Range: -5.3398

Max Act: 5.3398. Min Act: -0.1700

Data Index: 1551861 (Open Web Text)

Max Activating Token Index: 514

Text #1

Max Range: 5.3398. Min Range: -5.3398

Max Act: 5.1302. Min Act: -0.1700

Data Index: 2740218 (Open Web Text)

Max Activating Token Index: 402

Text #2

Max Range: 5.3398. Min Range: -5.3398

Max Act: 5.1707. Min Act: -0.1700

Data Index: 5959285 (Open Web Text)

Max Activating Token Index: 656

Text #3

Max Range: 5.3398. Min Range: -5.3398

Max Act: 5.1022. Min Act: -0.1700

Data Index: 3277889 (Open Web Text)

Max Activating Token Index: 693

Text #4

Max Range: 5.3398. Min Range: -5.3398

Max Act: 5.0703. Min Act: -0.1700

Data Index: 5138539 (Open Web Text)

Max Activating Token Index: 697

Text #5

Max Range: 5.3398. Min Range: -5.3398

Max Act: 5.0580. Min Act: -0.1700

Data Index: 1050828 (Open Web Text)

Max Activating Token Index: 798

Text #6

Max Range: 5.3398. Min Range: -5.3398

Max Act: 4.9826. Min Act: -0.1700

Data Index: 2084388 (Open Web Text)

Max Activating Token Index: 559

Text #7

Max Range: 5.3398. Min Range: -5.3398

Max Act: 4.9473. Min Act: -0.1700

Data Index: 1151548 (Open Web Text)

Max Activating Token Index: 908

Text #8

Max Range: 5.3398. Min Range: -5.3398

Max Act: 4.8800. Min Act: -0.1700

Data Index: 5221840 (Open Web Text)

Max Activating Token Index: 873

Text #9

Max Range: 5.3398. Min Range: -5.3398

Max Act: 4.8789. Min Act: -0.1700

Data Index: 2402051 (Open Web Text)

Max Activating Token Index: 853

Text #10

Max Range: 5.3398. Min Range: -5.3398

Max Act: 4.8224. Min Act: -0.1700

Data Index: 2642789 (Open Web Text)

Max Activating Token Index: 996

Text #11

Max Range: 5.3398. Min Range: -5.3398

Max Act: 4.8397. Min Act: -0.1700

Data Index: 8126430 (Open Web Text)

Max Activating Token Index: 564

Text #12

Max Range: 5.3398. Min Range: -5.3398

Max Act: 4.8391. Min Act: -0.1700

Data Index: 342151 (Open Web Text)

Max Activating Token Index: 260

Text #13

Max Range: 5.3398. Min Range: -5.3398

Max Act: 4.8811. Min Act: -0.1700

Data Index: 805271 (Open Web Text)

Max Activating Token Index: 367

Text #14

Max Range: 5.3398. Min Range: -5.3398

Max Act: 4.8231. Min Act: -0.1700

Data Index: 8813741 (Open Web Text)

Max Activating Token Index: 865

Text #15

Max Range: 5.3398. Min Range: -5.3398

Max Act: 4.8536. Min Act: -0.1700

Data Index: 2898527 (Open Web Text)

Max Activating Token Index: 917

Text #16

Max Range: 5.3398. Min Range: -5.3398

Max Act: 4.8598. Min Act: -0.1700

Data Index: 1048386 (Open Web Text)

Max Activating Token Index: 522

Text #17

Max Range: 5.3398. Min Range: -5.3398

Max Act: 4.8238. Min Act: -0.1700

Data Index: 935496 (Open Web Text)

Max Activating Token Index: 285

Text #18

Max Range: 5.3398. Min Range: -5.3398

Max Act: 4.8478. Min Act: -0.1700

Data Index: 2376920 (Open Web Text)

Max Activating Token Index: 773

Text #19

Max Range: 5.3398. Min Range: -5.3398

Max Act: 4.8282. Min Act: -0.1700

Data Index: 4461247 (Open Web Text)

Max Activating Token Index: 782