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

Dataset: Open Web Text

Neuron 1992 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: 4.2386. Min Range: -4.2386

Max Act: 4.1987. Min Act: -0.1700

Data Index: 1997061 (Open Web Text)

Max Activating Token Index: 689

Text #1

Max Range: 4.2386. Min Range: -4.2386

Max Act: 4.2386. Min Act: -0.1700

Data Index: 3840560 (Open Web Text)

Max Activating Token Index: 866

Text #2

Max Range: 4.2386. Min Range: -4.2386

Max Act: 4.1861. Min Act: -0.1700

Data Index: 8448882 (Open Web Text)

Max Activating Token Index: 445

Text #3

Max Range: 4.2386. Min Range: -4.2386

Max Act: 4.1828. Min Act: -0.1700

Data Index: 4309140 (Open Web Text)

Max Activating Token Index: 891

Text #4

Max Range: 4.2386. Min Range: -4.2386

Max Act: 4.1713. Min Act: -0.1700

Data Index: 4020891 (Open Web Text)

Max Activating Token Index: 27

Text #5

Max Range: 4.2386. Min Range: -4.2386

Max Act: 4.1711. Min Act: -0.1700

Data Index: 365953 (Open Web Text)

Max Activating Token Index: 124

Text #6

Max Range: 4.2386. Min Range: -4.2386

Max Act: 4.1069. Min Act: -0.1700

Data Index: 8043329 (Open Web Text)

Max Activating Token Index: 466

Text #7

Max Range: 4.2386. Min Range: -4.2386

Max Act: 4.1231. Min Act: -0.1700

Data Index: 5222089 (Open Web Text)

Max Activating Token Index: 999

Text #8

Max Range: 4.2386. Min Range: -4.2386

Max Act: 4.1298. Min Act: -0.1700

Data Index: 881017 (Open Web Text)

Max Activating Token Index: 549

Text #9

Max Range: 4.2386. Min Range: -4.2386

Max Act: 4.1091. Min Act: -0.1700

Data Index: 420529 (Open Web Text)

Max Activating Token Index: 732

Text #10

Max Range: 4.2386. Min Range: -4.2386

Max Act: 4.0853. Min Act: -0.1700

Data Index: 5265739 (Open Web Text)

Max Activating Token Index: 467

Text #11

Max Range: 4.2386. Min Range: -4.2386

Max Act: 4.0959. Min Act: -0.1700

Data Index: 1907849 (Open Web Text)

Max Activating Token Index: 959

Text #12

Max Range: 4.2386. Min Range: -4.2386

Max Act: 4.0990. Min Act: -0.1700

Data Index: 789518 (Open Web Text)

Max Activating Token Index: 953

Text #13

Max Range: 4.2386. Min Range: -4.2386

Max Act: 4.0682. Min Act: -0.1700

Data Index: 3871375 (Open Web Text)

Max Activating Token Index: 786

Text #14

Max Range: 4.2386. Min Range: -4.2386

Max Act: 4.0684. Min Act: -0.1700

Data Index: 6826960 (Open Web Text)

Max Activating Token Index: 715

Text #15

Max Range: 4.2386. Min Range: -4.2386

Max Act: 4.0589. Min Act: -0.1700

Data Index: 7921327 (Open Web Text)

Max Activating Token Index: 125

Text #16

Max Range: 4.2386. Min Range: -4.2386

Max Act: 4.0801. Min Act: -0.1700

Data Index: 647150 (Open Web Text)

Max Activating Token Index: 124

Text #17

Max Range: 4.2386. Min Range: -4.2386

Max Act: 4.0704. Min Act: -0.1700

Data Index: 1553532 (Open Web Text)

Max Activating Token Index: 164

Text #18

Max Range: 4.2386. Min Range: -4.2386

Max Act: 4.0312. Min Act: -0.1700

Data Index: 6436206 (Open Web Text)

Max Activating Token Index: 326

Text #19

Max Range: 4.2386. Min Range: -4.2386

Max Act: 4.0566. Min Act: -0.1700

Data Index: 1781465 (Open Web Text)

Max Activating Token Index: 468