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

Dataset: Open Web Text

Neuron 205 in Layer 4

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: 3.7604. Min Range: -3.7604

Max Act: 3.7604. Min Act: -0.1700

Data Index: 4730141 (Open Web Text)

Max Activating Token Index: 889

Text #1

Max Range: 3.7604. Min Range: -3.7604

Max Act: 3.7463. Min Act: -0.1700

Data Index: 5054985 (Open Web Text)

Max Activating Token Index: 447

Text #2

Max Range: 3.7604. Min Range: -3.7604

Max Act: 3.6900. Min Act: -0.1700

Data Index: 5455674 (Open Web Text)

Max Activating Token Index: 827

Text #3

Max Range: 3.7604. Min Range: -3.7604

Max Act: 3.6856. Min Act: -0.1700

Data Index: 641496 (Open Web Text)

Max Activating Token Index: 663

Text #4

Max Range: 3.7604. Min Range: -3.7604

Max Act: 3.6178. Min Act: -0.1700

Data Index: 1303594 (Open Web Text)

Max Activating Token Index: 958

Text #5

Max Range: 3.7604. Min Range: -3.7604

Max Act: 3.6625. Min Act: -0.1700

Data Index: 3155845 (Open Web Text)

Max Activating Token Index: 550

Text #6

Max Range: 3.7604. Min Range: -3.7604

Max Act: 3.6611. Min Act: -0.1700

Data Index: 6603336 (Open Web Text)

Max Activating Token Index: 377

Text #7

Max Range: 3.7604. Min Range: -3.7604

Max Act: 3.6465. Min Act: -0.1700

Data Index: 5451302 (Open Web Text)

Max Activating Token Index: 624

Text #8

Max Range: 3.7604. Min Range: -3.7604

Max Act: 3.6376. Min Act: -0.1700

Data Index: 3201076 (Open Web Text)

Max Activating Token Index: 800

Text #9

Max Range: 3.7604. Min Range: -3.7604

Max Act: 3.6276. Min Act: -0.1700

Data Index: 8789364 (Open Web Text)

Max Activating Token Index: 394

Text #10

Max Range: 3.7604. Min Range: -3.7604

Max Act: 3.6076. Min Act: -0.1700

Data Index: 1650274 (Open Web Text)

Max Activating Token Index: 75

Text #11

Max Range: 3.7604. Min Range: -3.7604

Max Act: 3.6299. Min Act: -0.1700

Data Index: 4724769 (Open Web Text)

Max Activating Token Index: 859

Text #12

Max Range: 3.7604. Min Range: -3.7604

Max Act: 3.5395. Min Act: -0.1700

Data Index: 2573803 (Open Web Text)

Max Activating Token Index: 765

Text #13

Max Range: 3.7604. Min Range: -3.7604

Max Act: 3.6179. Min Act: -0.1700

Data Index: 4301456 (Open Web Text)

Max Activating Token Index: 817

Text #14

Max Range: 3.7604. Min Range: -3.7604

Max Act: 3.5758. Min Act: -0.1700

Data Index: 6108105 (Open Web Text)

Max Activating Token Index: 604

Text #15

Max Range: 3.7604. Min Range: -3.7604

Max Act: 3.5785. Min Act: -0.1700

Data Index: 3688445 (Open Web Text)

Max Activating Token Index: 631

Text #16

Max Range: 3.7604. Min Range: -3.7604

Max Act: 3.5796. Min Act: -0.1700

Data Index: 7636263 (Open Web Text)

Max Activating Token Index: 500

Text #17

Max Range: 3.7604. Min Range: -3.7604

Max Act: 3.5777. Min Act: -0.1700

Data Index: 1872903 (Open Web Text)

Max Activating Token Index: 133

Text #18

Max Range: 3.7604. Min Range: -3.7604

Max Act: 3.5638. Min Act: -0.1700

Data Index: 197042 (Open Web Text)

Max Activating Token Index: 891

Text #19

Max Range: 3.7604. Min Range: -3.7604

Max Act: 3.5614. Min Act: -0.1700

Data Index: 1704667 (Open Web Text)

Max Activating Token Index: 497