Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 1720 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')

Text #0

Max Range: 5.8549. Min Range: -5.8549

Max Act: 5.8549. Min Act: -0.1700

Data Index: 4552913 (Open Web Text)

Max Activating Token Index: 642

Text #1

Max Range: 5.8549. Min Range: -5.8549

Max Act: 5.6049. Min Act: -0.1700

Data Index: 2268981 (Open Web Text)

Max Activating Token Index: 961

Text #2

Max Range: 5.8549. Min Range: -5.8549

Max Act: 5.6049. Min Act: -0.1700

Data Index: 3100215 (Open Web Text)

Max Activating Token Index: 161

Text #3

Max Range: 5.8549. Min Range: -5.8549

Max Act: 5.5736. Min Act: -0.1700

Data Index: 5537586 (Open Web Text)

Max Activating Token Index: 881

Text #4

Max Range: 5.8549. Min Range: -5.8549

Max Act: 5.5111. Min Act: -0.1700

Data Index: 5326739 (Open Web Text)

Max Activating Token Index: 492

Text #5

Max Range: 5.8549. Min Range: -5.8549

Max Act: 5.4799. Min Act: -0.1700

Data Index: 3822503 (Open Web Text)

Max Activating Token Index: 929

Text #6

Max Range: 5.8549. Min Range: -5.8549

Max Act: 5.4486. Min Act: -0.1700

Data Index: 1971710 (Open Web Text)

Max Activating Token Index: 767

Text #7

Max Range: 5.8549. Min Range: -5.8549

Max Act: 5.4486. Min Act: -0.1700

Data Index: 5003541 (Open Web Text)

Max Activating Token Index: 611

Text #8

Max Range: 5.8549. Min Range: -5.8549

Max Act: 5.4174. Min Act: -0.1700

Data Index: 7447169 (Open Web Text)

Max Activating Token Index: 418

Text #9

Max Range: 5.8549. Min Range: -5.8549

Max Act: 5.4174. Min Act: -0.1700

Data Index: 1335639 (Open Web Text)

Max Activating Token Index: 251

Text #10

Max Range: 5.8549. Min Range: -5.8549

Max Act: 5.4486. Min Act: -0.1700

Data Index: 2651532 (Open Web Text)

Max Activating Token Index: 719

Text #11

Max Range: 5.8549. Min Range: -5.8549

Max Act: 5.3861. Min Act: -0.1700

Data Index: 594420 (Open Web Text)

Max Activating Token Index: 167

Text #12

Max Range: 5.8549. Min Range: -5.8549

Max Act: 5.3861. Min Act: -0.1700

Data Index: 6774982 (Open Web Text)

Max Activating Token Index: 667

Text #13

Max Range: 5.8549. Min Range: -5.8549

Max Act: 5.3861. Min Act: -0.1700

Data Index: 4322553 (Open Web Text)

Max Activating Token Index: 828

Text #14

Max Range: 5.8549. Min Range: -5.8549

Max Act: 5.3236. Min Act: -0.1700

Data Index: 7014909 (Open Web Text)

Max Activating Token Index: 139

Text #15

Max Range: 5.8549. Min Range: -5.8549

Max Act: 5.3549. Min Act: -0.1700

Data Index: 7480755 (Open Web Text)

Max Activating Token Index: 540

Text #16

Max Range: 5.8549. Min Range: -5.8549

Max Act: 5.3549. Min Act: -0.1700

Data Index: 3327670 (Open Web Text)

Max Activating Token Index: 142

Text #17

Max Range: 5.8549. Min Range: -5.8549

Max Act: 5.3549. Min Act: -0.1700

Data Index: 4210187 (Open Web Text)

Max Activating Token Index: 457

Text #18

Max Range: 5.8549. Min Range: -5.8549

Max Act: 5.3549. Min Act: -0.1700

Data Index: 2758713 (Open Web Text)

Max Activating Token Index: 934

Text #19

Max Range: 5.8549. Min Range: -5.8549

Max Act: 5.3236. Min Act: -0.1700

Data Index: 7137852 (Open Web Text)

Max Activating Token Index: 486