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

Dataset: Open Web Text

Neuron 107 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: 1.9719. Min Range: -1.9719

Max Act: 1.9708. Min Act: -0.1700

Data Index: 4535008 (Open Web Text)

Max Activating Token Index: 216

Text #1

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.9579. Min Act: -0.1700

Data Index: 4285926 (Open Web Text)

Max Activating Token Index: 16

Text #2

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.9719. Min Act: -0.1700

Data Index: 287234 (Open Web Text)

Max Activating Token Index: 924

Text #3

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.9493. Min Act: -0.1700

Data Index: 616104 (Open Web Text)

Max Activating Token Index: 109

Text #4

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.9385. Min Act: -0.1700

Data Index: 1365597 (Open Web Text)

Max Activating Token Index: 287

Text #5

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.9446. Min Act: -0.1700

Data Index: 6366311 (Open Web Text)

Max Activating Token Index: 467

Text #6

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.9635. Min Act: -0.1700

Data Index: 2870769 (Open Web Text)

Max Activating Token Index: 704

Text #7

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.9390. Min Act: -0.1700

Data Index: 6090032 (Open Web Text)

Max Activating Token Index: 515

Text #8

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.9372. Min Act: -0.1700

Data Index: 1233785 (Open Web Text)

Max Activating Token Index: 128

Text #9

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.9270. Min Act: -0.1700

Data Index: 4216447 (Open Web Text)

Max Activating Token Index: 959

Text #10

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.9303. Min Act: -0.1700

Data Index: 7265382 (Open Web Text)

Max Activating Token Index: 82

Text #11

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.9258. Min Act: -0.1700

Data Index: 6539445 (Open Web Text)

Max Activating Token Index: 387

Text #12

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.9297. Min Act: -0.1700

Data Index: 5513988 (Open Web Text)

Max Activating Token Index: 175

Text #13

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.9352. Min Act: -0.1700

Data Index: 4745836 (Open Web Text)

Max Activating Token Index: 28

Text #14

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.9133. Min Act: -0.1700

Data Index: 3306685 (Open Web Text)

Max Activating Token Index: 939

Text #15

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.9097. Min Act: -0.1700

Data Index: 1623938 (Open Web Text)

Max Activating Token Index: 940

Text #16

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.9041. Min Act: -0.1700

Data Index: 3229714 (Open Web Text)

Max Activating Token Index: 118

Text #17

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.9285. Min Act: -0.1700

Data Index: 4571342 (Open Web Text)

Max Activating Token Index: 594

Text #18

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.9214. Min Act: -0.1700

Data Index: 1802772 (Open Web Text)

Max Activating Token Index: 799

Text #19

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.9067. Min Act: -0.1700

Data Index: 7717678 (Open Web Text)

Max Activating Token Index: 342