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

Dataset: Open Web Text

Neuron 1723 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: 1.7615. Min Range: -1.7615

Max Act: 1.7615. Min Act: -0.1700

Data Index: 1372501 (Open Web Text)

Max Activating Token Index: 515

Text #1

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.7215. Min Act: -0.1700

Data Index: 2384525 (Open Web Text)

Max Activating Token Index: 168

Text #2

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.7229. Min Act: -0.1699

Data Index: 1096079 (Open Web Text)

Max Activating Token Index: 675

Text #3

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.7065. Min Act: -0.1700

Data Index: 2864323 (Open Web Text)

Max Activating Token Index: 107

Text #4

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.6964. Min Act: -0.1700

Data Index: 378063 (Open Web Text)

Max Activating Token Index: 869

Text #5

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.6847. Min Act: -0.1700

Data Index: 5513568 (Open Web Text)

Max Activating Token Index: 84

Text #6

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.6734. Min Act: -0.1695

Data Index: 6952826 (Open Web Text)

Max Activating Token Index: 658

Text #7

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.6762. Min Act: -0.1700

Data Index: 4993342 (Open Web Text)

Max Activating Token Index: 203

Text #8

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.6777. Min Act: -0.1700

Data Index: 6124054 (Open Web Text)

Max Activating Token Index: 254

Text #9

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.6609. Min Act: -0.1700

Data Index: 4510713 (Open Web Text)

Max Activating Token Index: 124

Text #10

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.6555. Min Act: -0.1700

Data Index: 814580 (Open Web Text)

Max Activating Token Index: 562

Text #11

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.6436. Min Act: -0.1700

Data Index: 8368627 (Open Web Text)

Max Activating Token Index: 912

Text #12

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.6523. Min Act: -0.1700

Data Index: 8509515 (Open Web Text)

Max Activating Token Index: 874

Text #13

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.6455. Min Act: -0.1700

Data Index: 3633106 (Open Web Text)

Max Activating Token Index: 443

Text #14

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.6441. Min Act: -0.1700

Data Index: 6472855 (Open Web Text)

Max Activating Token Index: 101

Text #15

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.6365. Min Act: -0.1700

Data Index: 2520428 (Open Web Text)

Max Activating Token Index: 728

Text #16

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.6276. Min Act: -0.1699

Data Index: 357186 (Open Web Text)

Max Activating Token Index: 826

Text #17

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.6274. Min Act: -0.1700

Data Index: 5513566 (Open Web Text)

Max Activating Token Index: 890

Text #18

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.6203. Min Act: -0.1700

Data Index: 1903773 (Open Web Text)

Max Activating Token Index: 435

Text #19

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.6196. Min Act: -0.1700

Data Index: 107722 (Open Web Text)

Max Activating Token Index: 76