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

Dataset: Open Web Text

Neuron 309 in Layer 0

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: 3.3534. Min Range: -3.3534

Max Act: 3.3521. Min Act: -0.1700

Data Index: 811450 (Open Web Text)

Max Activating Token Index: 385

Text #1

Max Range: 3.3534. Min Range: -3.3534

Max Act: 3.3534. Min Act: -0.1700

Data Index: 4688634 (Open Web Text)

Max Activating Token Index: 34

Text #2

Max Range: 3.3534. Min Range: -3.3534

Max Act: 3.3314. Min Act: -0.1700

Data Index: 5472890 (Open Web Text)

Max Activating Token Index: 205

Text #3

Max Range: 3.3534. Min Range: -3.3534

Max Act: 3.3083. Min Act: -0.1700

Data Index: 7989239 (Open Web Text)

Max Activating Token Index: 143

Text #4

Max Range: 3.3534. Min Range: -3.3534

Max Act: 3.2860. Min Act: -0.1700

Data Index: 7757181 (Open Web Text)

Max Activating Token Index: 487

Text #5

Max Range: 3.3534. Min Range: -3.3534

Max Act: 3.2953. Min Act: -0.1700

Data Index: 4191763 (Open Web Text)

Max Activating Token Index: 46

Text #6

Max Range: 3.3534. Min Range: -3.3534

Max Act: 3.2831. Min Act: -0.1700

Data Index: 985437 (Open Web Text)

Max Activating Token Index: 387

Text #7

Max Range: 3.3534. Min Range: -3.3534

Max Act: 3.2641. Min Act: -0.1700

Data Index: 4769279 (Open Web Text)

Max Activating Token Index: 653

Text #8

Max Range: 3.3534. Min Range: -3.3534

Max Act: 3.2622. Min Act: -0.1700

Data Index: 4427787 (Open Web Text)

Max Activating Token Index: 142

Text #9

Max Range: 3.3534. Min Range: -3.3534

Max Act: 3.2602. Min Act: -0.1700

Data Index: 5515404 (Open Web Text)

Max Activating Token Index: 963

Text #10

Max Range: 3.3534. Min Range: -3.3534

Max Act: 3.2653. Min Act: -0.1700

Data Index: 5627729 (Open Web Text)

Max Activating Token Index: 688

Text #11

Max Range: 3.3534. Min Range: -3.3534

Max Act: 3.2708. Min Act: -0.1700

Data Index: 1783368 (Open Web Text)

Max Activating Token Index: 729

Text #12

Max Range: 3.3534. Min Range: -3.3534

Max Act: 3.2720. Min Act: -0.1700

Data Index: 989710 (Open Web Text)

Max Activating Token Index: 608

Text #13

Max Range: 3.3534. Min Range: -3.3534

Max Act: 3.2627. Min Act: -0.1700

Data Index: 6978737 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 3.3534. Min Range: -3.3534

Max Act: 3.2400. Min Act: -0.1700

Data Index: 209299 (Open Web Text)

Max Activating Token Index: 710

Text #15

Max Range: 3.3534. Min Range: -3.3534

Max Act: 3.2528. Min Act: -0.1700

Data Index: 5114633 (Open Web Text)

Max Activating Token Index: 853

Text #16

Max Range: 3.3534. Min Range: -3.3534

Max Act: 3.2391. Min Act: -0.1700

Data Index: 4191733 (Open Web Text)

Max Activating Token Index: 818

Text #17

Max Range: 3.3534. Min Range: -3.3534

Max Act: 3.2423. Min Act: -0.1700

Data Index: 2948907 (Open Web Text)

Max Activating Token Index: 125

Text #18

Max Range: 3.3534. Min Range: -3.3534

Max Act: 3.2311. Min Act: -0.1700

Data Index: 7734947 (Open Web Text)

Max Activating Token Index: 718

Text #19

Max Range: 3.3534. Min Range: -3.3534

Max Act: 3.2203. Min Act: -0.1700

Data Index: 1754373 (Open Web Text)

Max Activating Token Index: 109