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

Dataset: Open Web Text

Neuron 755 in Layer 1

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: 5.3410. Min Range: -5.3410

Max Act: 5.3410. Min Act: -0.1700

Data Index: 5205384 (Open Web Text)

Max Activating Token Index: 373

Text #1

Max Range: 5.3410. Min Range: -5.3410

Max Act: 5.3000. Min Act: -0.1700

Data Index: 7248288 (Open Web Text)

Max Activating Token Index: 645

Text #2

Max Range: 5.3410. Min Range: -5.3410

Max Act: 5.2812. Min Act: -0.1700

Data Index: 5692256 (Open Web Text)

Max Activating Token Index: 281

Text #3

Max Range: 5.3410. Min Range: -5.3410

Max Act: 5.2618. Min Act: -0.1700

Data Index: 5991549 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 5.3410. Min Range: -5.3410

Max Act: 5.2989. Min Act: -0.1700

Data Index: 6047702 (Open Web Text)

Max Activating Token Index: 750

Text #5

Max Range: 5.3410. Min Range: -5.3410

Max Act: 5.2732. Min Act: -0.1700

Data Index: 6758426 (Open Web Text)

Max Activating Token Index: 334

Text #6

Max Range: 5.3410. Min Range: -5.3410

Max Act: 5.2772. Min Act: -0.1700

Data Index: 7726414 (Open Web Text)

Max Activating Token Index: 659

Text #7

Max Range: 5.3410. Min Range: -5.3410

Max Act: 5.2608. Min Act: -0.1700

Data Index: 5331392 (Open Web Text)

Max Activating Token Index: 393

Text #8

Max Range: 5.3410. Min Range: -5.3410

Max Act: 5.2795. Min Act: -0.1700

Data Index: 2948086 (Open Web Text)

Max Activating Token Index: 455

Text #9

Max Range: 5.3410. Min Range: -5.3410

Max Act: 5.2587. Min Act: -0.1700

Data Index: 1456596 (Open Web Text)

Max Activating Token Index: 14

Text #10

Max Range: 5.3410. Min Range: -5.3410

Max Act: 5.2537. Min Act: -0.1700

Data Index: 4173117 (Open Web Text)

Max Activating Token Index: 234

Text #11

Max Range: 5.3410. Min Range: -5.3410

Max Act: 5.2386. Min Act: -0.1700

Data Index: 1070890 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 5.3410. Min Range: -5.3410

Max Act: 5.2166. Min Act: -0.1700

Data Index: 3121801 (Open Web Text)

Max Activating Token Index: 346

Text #13

Max Range: 5.3410. Min Range: -5.3410

Max Act: 5.2372. Min Act: -0.1700

Data Index: 4837261 (Open Web Text)

Max Activating Token Index: 104

Text #14

Max Range: 5.3410. Min Range: -5.3410

Max Act: 5.2405. Min Act: -0.1700

Data Index: 4769467 (Open Web Text)

Max Activating Token Index: 800

Text #15

Max Range: 5.3410. Min Range: -5.3410

Max Act: 5.2276. Min Act: -0.1700

Data Index: 3674562 (Open Web Text)

Max Activating Token Index: 782

Text #16

Max Range: 5.3410. Min Range: -5.3410

Max Act: 5.2132. Min Act: -0.1700

Data Index: 1516439 (Open Web Text)

Max Activating Token Index: 684

Text #17

Max Range: 5.3410. Min Range: -5.3410

Max Act: 5.1962. Min Act: -0.1700

Data Index: 520393 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 5.3410. Min Range: -5.3410

Max Act: 5.2186. Min Act: -0.1700

Data Index: 2566820 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 5.3410. Min Range: -5.3410

Max Act: 5.2109. Min Act: -0.1700

Data Index: 3566710 (Open Web Text)

Max Activating Token Index: 176