Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer

Dataset: Open Web Text

Neuron 3464 in Layer 21

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.7571. Min Act: -0.1700

Data Index: 1941085 (Open Web Text)

Max Activating Token Index: 1011

Text #1

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.6633. Min Act: -0.1700

Data Index: 5994911 (Open Web Text)

Max Activating Token Index: 495

Text #2

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.6008. Min Act: -0.1700

Data Index: 1831333 (Open Web Text)

Max Activating Token Index: 904

Text #3

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.5383. Min Act: -0.1700

Data Index: 5946833 (Open Web Text)

Max Activating Token Index: 803

Text #4

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.5383. Min Act: -0.1700

Data Index: 5558620 (Open Web Text)

Max Activating Token Index: 716

Text #5

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.5071. Min Act: -0.1700

Data Index: 4746601 (Open Web Text)

Max Activating Token Index: 704

Text #6

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.5071. Min Act: -0.1700

Data Index: 7209317 (Open Web Text)

Max Activating Token Index: 105

Text #7

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.5071. Min Act: -0.1700

Data Index: 1632807 (Open Web Text)

Max Activating Token Index: 261

Text #8

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.5071. Min Act: -0.1700

Data Index: 7404547 (Open Web Text)

Max Activating Token Index: 538

Text #9

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.5383. Min Act: -0.1700

Data Index: 6892296 (Open Web Text)

Max Activating Token Index: 751

Text #10

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.4758. Min Act: -0.1700

Data Index: 4368364 (Open Web Text)

Max Activating Token Index: 798

Text #11

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.5071. Min Act: -0.1700

Data Index: 6852192 (Open Web Text)

Max Activating Token Index: 142

Text #12

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.4446. Min Act: -0.1700

Data Index: 3770544 (Open Web Text)

Max Activating Token Index: 815

Text #13

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.4446. Min Act: -0.1700

Data Index: 1051988 (Open Web Text)

Max Activating Token Index: 395

Text #14

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.3821. Min Act: -0.1700

Data Index: 7802881 (Open Web Text)

Max Activating Token Index: 79

Text #15

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.4133. Min Act: -0.1700

Data Index: 2671020 (Open Web Text)

Max Activating Token Index: 123

Text #16

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.3821. Min Act: -0.1700

Data Index: 3966374 (Open Web Text)

Max Activating Token Index: 125

Text #17

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.3821. Min Act: -0.1700

Data Index: 5913459 (Open Web Text)

Max Activating Token Index: 298

Text #18

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.3508. Min Act: -0.1700

Data Index: 5289056 (Open Web Text)

Max Activating Token Index: 191

Text #19

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.3821. Min Act: -0.1700

Data Index: 4264909 (Open Web Text)

Max Activating Token Index: 176