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

Dataset: Open Web Text

Neuron 1708 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: 3.1652. Min Range: -3.1652

Max Act: 3.1652. Min Act: -0.1700

Data Index: 7794238 (Open Web Text)

Max Activating Token Index: 292

Text #1

Max Range: 3.1652. Min Range: -3.1652

Max Act: 3.0613. Min Act: -0.1700

Data Index: 3343016 (Open Web Text)

Max Activating Token Index: 881

Text #2

Max Range: 3.1652. Min Range: -3.1652

Max Act: 3.0728. Min Act: -0.1700

Data Index: 5157391 (Open Web Text)

Max Activating Token Index: 915

Text #3

Max Range: 3.1652. Min Range: -3.1652

Max Act: 3.0643. Min Act: -0.1700

Data Index: 7309213 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 3.1652. Min Range: -3.1652

Max Act: 3.0405. Min Act: -0.1700

Data Index: 2254074 (Open Web Text)

Max Activating Token Index: 571

Text #5

Max Range: 3.1652. Min Range: -3.1652

Max Act: 2.9533. Min Act: -0.1700

Data Index: 1955705 (Open Web Text)

Max Activating Token Index: 203

Text #6

Max Range: 3.1652. Min Range: -3.1652

Max Act: 3.0073. Min Act: -0.1700

Data Index: 1705363 (Open Web Text)

Max Activating Token Index: 507

Text #7

Max Range: 3.1652. Min Range: -3.1652

Max Act: 2.9823. Min Act: -0.1700

Data Index: 1264421 (Open Web Text)

Max Activating Token Index: 994

Text #8

Max Range: 3.1652. Min Range: -3.1652

Max Act: 2.9684. Min Act: -0.1700

Data Index: 6456985 (Open Web Text)

Max Activating Token Index: 562

Text #9

Max Range: 3.1652. Min Range: -3.1652

Max Act: 2.9927. Min Act: -0.1700

Data Index: 3419479 (Open Web Text)

Max Activating Token Index: 867

Text #10

Max Range: 3.1652. Min Range: -3.1652

Max Act: 2.9689. Min Act: -0.1700

Data Index: 7441665 (Open Web Text)

Max Activating Token Index: 502

Text #11

Max Range: 3.1652. Min Range: -3.1652

Max Act: 2.9314. Min Act: -0.1700

Data Index: 7942461 (Open Web Text)

Max Activating Token Index: 904

Text #12

Max Range: 3.1652. Min Range: -3.1652

Max Act: 2.9576. Min Act: -0.1700

Data Index: 2203009 (Open Web Text)

Max Activating Token Index: 16

Text #13

Max Range: 3.1652. Min Range: -3.1652

Max Act: 2.9679. Min Act: -0.1700

Data Index: 8446597 (Open Web Text)

Max Activating Token Index: 847

Text #14

Max Range: 3.1652. Min Range: -3.1652

Max Act: 2.9443. Min Act: -0.1700

Data Index: 1267620 (Open Web Text)

Max Activating Token Index: 775

Text #15

Max Range: 3.1652. Min Range: -3.1652

Max Act: 2.9692. Min Act: -0.1700

Data Index: 3091082 (Open Web Text)

Max Activating Token Index: 410

Text #16

Max Range: 3.1652. Min Range: -3.1652

Max Act: 2.9703. Min Act: -0.1700

Data Index: 7597928 (Open Web Text)

Max Activating Token Index: 157

Text #17

Max Range: 3.1652. Min Range: -3.1652

Max Act: 2.9413. Min Act: -0.1700

Data Index: 4828050 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.1652. Min Range: -3.1652

Max Act: 2.9473. Min Act: -0.1700

Data Index: 1387319 (Open Web Text)

Max Activating Token Index: 776

Text #19

Max Range: 3.1652. Min Range: -3.1652

Max Act: 2.9413. Min Act: -0.1700

Data Index: 5169581 (Open Web Text)

Max Activating Token Index: 3