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

Dataset: Open Web Text

Neuron 2000 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: 3.2762. Min Range: -3.2762

Max Act: 3.2477. Min Act: -0.1700

Data Index: 7510075 (Open Web Text)

Max Activating Token Index: 423

Text #1

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.2762. Min Act: -0.1700

Data Index: 6172920 (Open Web Text)

Max Activating Token Index: 249

Text #2

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.2556. Min Act: -0.1700

Data Index: 3119194 (Open Web Text)

Max Activating Token Index: 353

Text #3

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.2345. Min Act: -0.1700

Data Index: 6026009 (Open Web Text)

Max Activating Token Index: 446

Text #4

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.2456. Min Act: -0.1700

Data Index: 5792503 (Open Web Text)

Max Activating Token Index: 455

Text #5

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.2263. Min Act: -0.1700

Data Index: 2672511 (Open Web Text)

Max Activating Token Index: 111

Text #6

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.2305. Min Act: -0.1700

Data Index: 1499247 (Open Web Text)

Max Activating Token Index: 896

Text #7

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.2346. Min Act: -0.1700

Data Index: 2888137 (Open Web Text)

Max Activating Token Index: 668

Text #8

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.2308. Min Act: -0.1700

Data Index: 8697825 (Open Web Text)

Max Activating Token Index: 298

Text #9

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.2151. Min Act: -0.1700

Data Index: 4886903 (Open Web Text)

Max Activating Token Index: 857

Text #10

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.1921. Min Act: -0.1700

Data Index: 4181041 (Open Web Text)

Max Activating Token Index: 724

Text #11

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.2017. Min Act: -0.1700

Data Index: 8181899 (Open Web Text)

Max Activating Token Index: 256

Text #12

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.1833. Min Act: -0.1700

Data Index: 6570540 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.1941. Min Act: -0.1700

Data Index: 3800066 (Open Web Text)

Max Activating Token Index: 92

Text #14

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.1691. Min Act: -0.1700

Data Index: 1969687 (Open Web Text)

Max Activating Token Index: 92

Text #15

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.1726. Min Act: -0.1700

Data Index: 3806857 (Open Web Text)

Max Activating Token Index: 781

Text #16

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.1647. Min Act: -0.1700

Data Index: 3326413 (Open Web Text)

Max Activating Token Index: 632

Text #17

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.1641. Min Act: -0.1700

Data Index: 7367379 (Open Web Text)

Max Activating Token Index: 942

Text #18

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.1663. Min Act: -0.1700

Data Index: 3770267 (Open Web Text)

Max Activating Token Index: 220

Text #19

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.1477. Min Act: -0.1700

Data Index: 6601071 (Open Web Text)

Max Activating Token Index: 613