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

Dataset: Open Web Text

Neuron 1371 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: 4.2023. Min Range: -4.2023

Max Act: 4.2023. Min Act: -0.1700

Data Index: 6208734 (Open Web Text)

Max Activating Token Index: 666

Text #1

Max Range: 4.2023. Min Range: -4.2023

Max Act: 4.1672. Min Act: -0.1700

Data Index: 659373 (Open Web Text)

Max Activating Token Index: 1015

Text #2

Max Range: 4.2023. Min Range: -4.2023

Max Act: 4.1351. Min Act: -0.1700

Data Index: 6092708 (Open Web Text)

Max Activating Token Index: 613

Text #3

Max Range: 4.2023. Min Range: -4.2023

Max Act: 4.1188. Min Act: -0.1700

Data Index: 6956455 (Open Web Text)

Max Activating Token Index: 900

Text #4

Max Range: 4.2023. Min Range: -4.2023

Max Act: 4.1139. Min Act: -0.1700

Data Index: 7594011 (Open Web Text)

Max Activating Token Index: 165

Text #5

Max Range: 4.2023. Min Range: -4.2023

Max Act: 4.1557. Min Act: -0.1700

Data Index: 4045243 (Open Web Text)

Max Activating Token Index: 932

Text #6

Max Range: 4.2023. Min Range: -4.2023

Max Act: 4.1392. Min Act: -0.1700

Data Index: 7518399 (Open Web Text)

Max Activating Token Index: 580

Text #7

Max Range: 4.2023. Min Range: -4.2023

Max Act: 4.1233. Min Act: -0.1700

Data Index: 4517531 (Open Web Text)

Max Activating Token Index: 126

Text #8

Max Range: 4.2023. Min Range: -4.2023

Max Act: 4.0615. Min Act: -0.1700

Data Index: 3959478 (Open Web Text)

Max Activating Token Index: 33

Text #9

Max Range: 4.2023. Min Range: -4.2023

Max Act: 4.1066. Min Act: -0.1700

Data Index: 7342544 (Open Web Text)

Max Activating Token Index: 321

Text #10

Max Range: 4.2023. Min Range: -4.2023

Max Act: 4.1080. Min Act: -0.1700

Data Index: 7125966 (Open Web Text)

Max Activating Token Index: 630

Text #11

Max Range: 4.2023. Min Range: -4.2023

Max Act: 4.1197. Min Act: -0.1700

Data Index: 8831467 (Open Web Text)

Max Activating Token Index: 633

Text #12

Max Range: 4.2023. Min Range: -4.2023

Max Act: 4.1067. Min Act: -0.1700

Data Index: 710469 (Open Web Text)

Max Activating Token Index: 14

Text #13

Max Range: 4.2023. Min Range: -4.2023

Max Act: 4.1248. Min Act: -0.1700

Data Index: 1546350 (Open Web Text)

Max Activating Token Index: 477

Text #14

Max Range: 4.2023. Min Range: -4.2023

Max Act: 4.0753. Min Act: -0.1700

Data Index: 327396 (Open Web Text)

Max Activating Token Index: 495

Text #15

Max Range: 4.2023. Min Range: -4.2023

Max Act: 4.0974. Min Act: -0.1700

Data Index: 7140542 (Open Web Text)

Max Activating Token Index: 964

Text #16

Max Range: 4.2023. Min Range: -4.2023

Max Act: 4.0592. Min Act: -0.1700

Data Index: 3403018 (Open Web Text)

Max Activating Token Index: 705

Text #17

Max Range: 4.2023. Min Range: -4.2023

Max Act: 4.0727. Min Act: -0.1700

Data Index: 5853146 (Open Web Text)

Max Activating Token Index: 436

Text #18

Max Range: 4.2023. Min Range: -4.2023

Max Act: 4.0231. Min Act: -0.1700

Data Index: 4319287 (Open Web Text)

Max Activating Token Index: 711

Text #19

Max Range: 4.2023. Min Range: -4.2023

Max Act: 4.0369. Min Act: -0.1700

Data Index: 837901 (Open Web Text)

Max Activating Token Index: 233