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

Dataset: Open Web Text

Neuron 1150 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: 4.1410. Min Range: -4.1410

Max Act: 4.1410. Min Act: -0.1700

Data Index: 4561857 (Open Web Text)

Max Activating Token Index: 146

Text #1

Max Range: 4.1410. Min Range: -4.1410

Max Act: 4.1193. Min Act: -0.1700

Data Index: 3118204 (Open Web Text)

Max Activating Token Index: 767

Text #2

Max Range: 4.1410. Min Range: -4.1410

Max Act: 4.0749. Min Act: -0.1700

Data Index: 1735067 (Open Web Text)

Max Activating Token Index: 835

Text #3

Max Range: 4.1410. Min Range: -4.1410

Max Act: 4.0653. Min Act: -0.1700

Data Index: 7414974 (Open Web Text)

Max Activating Token Index: 274

Text #4

Max Range: 4.1410. Min Range: -4.1410

Max Act: 4.0703. Min Act: -0.1700

Data Index: 8056198 (Open Web Text)

Max Activating Token Index: 470

Text #5

Max Range: 4.1410. Min Range: -4.1410

Max Act: 4.0637. Min Act: -0.1700

Data Index: 1893708 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 4.1410. Min Range: -4.1410

Max Act: 4.0470. Min Act: -0.1700

Data Index: 8607289 (Open Web Text)

Max Activating Token Index: 641

Text #7

Max Range: 4.1410. Min Range: -4.1410

Max Act: 4.0414. Min Act: -0.1700

Data Index: 6194540 (Open Web Text)

Max Activating Token Index: 261

Text #8

Max Range: 4.1410. Min Range: -4.1410

Max Act: 4.0108. Min Act: -0.1700

Data Index: 1833914 (Open Web Text)

Max Activating Token Index: 550

Text #9

Max Range: 4.1410. Min Range: -4.1410

Max Act: 4.0492. Min Act: -0.1700

Data Index: 5887883 (Open Web Text)

Max Activating Token Index: 618

Text #10

Max Range: 4.1410. Min Range: -4.1410

Max Act: 4.0343. Min Act: -0.1700

Data Index: 1300712 (Open Web Text)

Max Activating Token Index: 128

Text #11

Max Range: 4.1410. Min Range: -4.1410

Max Act: 4.0219. Min Act: -0.1700

Data Index: 1099728 (Open Web Text)

Max Activating Token Index: 724

Text #12

Max Range: 4.1410. Min Range: -4.1410

Max Act: 4.0178. Min Act: -0.1700

Data Index: 8198144 (Open Web Text)

Max Activating Token Index: 768

Text #13

Max Range: 4.1410. Min Range: -4.1410

Max Act: 4.0443. Min Act: -0.1700

Data Index: 2279141 (Open Web Text)

Max Activating Token Index: 413

Text #14

Max Range: 4.1410. Min Range: -4.1410

Max Act: 3.9868. Min Act: -0.1700

Data Index: 3182208 (Open Web Text)

Max Activating Token Index: 541

Text #15

Max Range: 4.1410. Min Range: -4.1410

Max Act: 3.9847. Min Act: -0.1700

Data Index: 4385935 (Open Web Text)

Max Activating Token Index: 813

Text #16

Max Range: 4.1410. Min Range: -4.1410

Max Act: 3.9919. Min Act: -0.1700

Data Index: 5499867 (Open Web Text)

Max Activating Token Index: 157

Text #17

Max Range: 4.1410. Min Range: -4.1410

Max Act: 4.0014. Min Act: -0.1700

Data Index: 8215187 (Open Web Text)

Max Activating Token Index: 387

Text #18

Max Range: 4.1410. Min Range: -4.1410

Max Act: 3.9821. Min Act: -0.1700

Data Index: 6903337 (Open Web Text)

Max Activating Token Index: 271

Text #19

Max Range: 4.1410. Min Range: -4.1410

Max Act: 4.0022. Min Act: -0.1700

Data Index: 6792782 (Open Web Text)

Max Activating Token Index: 199