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

Dataset: Open Web Text

Neuron 1075 in Layer 5

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: 2.8410. Min Range: -2.8410

Max Act: 2.8410. Min Act: -0.1700

Data Index: 8206026 (Open Web Text)

Max Activating Token Index: 972

Text #1

Max Range: 2.8410. Min Range: -2.8410

Max Act: 2.8204. Min Act: -0.1700

Data Index: 7903616 (Open Web Text)

Max Activating Token Index: 454

Text #2

Max Range: 2.8410. Min Range: -2.8410

Max Act: 2.8202. Min Act: -0.1700

Data Index: 4272982 (Open Web Text)

Max Activating Token Index: 615

Text #3

Max Range: 2.8410. Min Range: -2.8410

Max Act: 2.8010. Min Act: -0.1700

Data Index: 3208697 (Open Web Text)

Max Activating Token Index: 770

Text #4

Max Range: 2.8410. Min Range: -2.8410

Max Act: 2.8113. Min Act: -0.1700

Data Index: 1588279 (Open Web Text)

Max Activating Token Index: 946

Text #5

Max Range: 2.8410. Min Range: -2.8410

Max Act: 2.7272. Min Act: -0.1700

Data Index: 8829483 (Open Web Text)

Max Activating Token Index: 766

Text #6

Max Range: 2.8410. Min Range: -2.8410

Max Act: 2.7246. Min Act: -0.1700

Data Index: 6076984 (Open Web Text)

Max Activating Token Index: 584

Text #7

Max Range: 2.8410. Min Range: -2.8410

Max Act: 2.6861. Min Act: -0.1700

Data Index: 3122027 (Open Web Text)

Max Activating Token Index: 503

Text #8

Max Range: 2.8410. Min Range: -2.8410

Max Act: 2.6934. Min Act: -0.1700

Data Index: 131062 (Open Web Text)

Max Activating Token Index: 635

Text #9

Max Range: 2.8410. Min Range: -2.8410

Max Act: 2.6687. Min Act: -0.1700

Data Index: 5475057 (Open Web Text)

Max Activating Token Index: 96

Text #10

Max Range: 2.8410. Min Range: -2.8410

Max Act: 2.6734. Min Act: -0.1700

Data Index: 5746619 (Open Web Text)

Max Activating Token Index: 975

Text #11

Max Range: 2.8410. Min Range: -2.8410

Max Act: 2.6772. Min Act: -0.1700

Data Index: 7816249 (Open Web Text)

Max Activating Token Index: 607

Text #12

Max Range: 2.8410. Min Range: -2.8410

Max Act: 2.6475. Min Act: -0.1700

Data Index: 649205 (Open Web Text)

Max Activating Token Index: 106

Text #13

Max Range: 2.8410. Min Range: -2.8410

Max Act: 2.6479. Min Act: -0.1700

Data Index: 7746011 (Open Web Text)

Max Activating Token Index: 460

Text #14

Max Range: 2.8410. Min Range: -2.8410

Max Act: 2.6488. Min Act: -0.1700

Data Index: 3293015 (Open Web Text)

Max Activating Token Index: 956

Text #15

Max Range: 2.8410. Min Range: -2.8410

Max Act: 2.6217. Min Act: -0.1700

Data Index: 1235106 (Open Web Text)

Max Activating Token Index: 477

Text #16

Max Range: 2.8410. Min Range: -2.8410

Max Act: 2.6555. Min Act: -0.1700

Data Index: 7669252 (Open Web Text)

Max Activating Token Index: 455

Text #17

Max Range: 2.8410. Min Range: -2.8410

Max Act: 2.6372. Min Act: -0.1700

Data Index: 2271693 (Open Web Text)

Max Activating Token Index: 736

Text #18

Max Range: 2.8410. Min Range: -2.8410

Max Act: 2.6402. Min Act: -0.1700

Data Index: 7354156 (Open Web Text)

Max Activating Token Index: 463

Text #19

Max Range: 2.8410. Min Range: -2.8410

Max Act: 2.6328. Min Act: -0.1700

Data Index: 2249791 (Open Web Text)

Max Activating Token Index: 880