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

Dataset: Open Web Text

Neuron 750 in Layer 38

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.7571. Min Act: -0.1700

Data Index: 5538654 (Open Web Text)

Max Activating Token Index: 633

Text #1

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.7258. Min Act: -0.1700

Data Index: 1104392 (Open Web Text)

Max Activating Token Index: 76

Text #2

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.7258. Min Act: -0.1700

Data Index: 1579621 (Open Web Text)

Max Activating Token Index: 788

Text #3

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.7571. Min Act: -0.1700

Data Index: 8816847 (Open Web Text)

Max Activating Token Index: 501

Text #4

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.6946. Min Act: -0.1700

Data Index: 8620197 (Open Web Text)

Max Activating Token Index: 690

Text #5

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.6946. Min Act: -0.1700

Data Index: 2107166 (Open Web Text)

Max Activating Token Index: 942

Text #6

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.6946. Min Act: -0.1700

Data Index: 5207262 (Open Web Text)

Max Activating Token Index: 728

Text #7

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.6633. Min Act: -0.1700

Data Index: 3584011 (Open Web Text)

Max Activating Token Index: 474

Text #8

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.6946. Min Act: -0.1700

Data Index: 4525838 (Open Web Text)

Max Activating Token Index: 254

Text #9

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.6633. Min Act: -0.1700

Data Index: 5709449 (Open Web Text)

Max Activating Token Index: 302

Text #10

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.6633. Min Act: -0.1700

Data Index: 1184526 (Open Web Text)

Max Activating Token Index: 864

Text #11

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.6321. Min Act: -0.1700

Data Index: 5185382 (Open Web Text)

Max Activating Token Index: 281

Text #12

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.6321. Min Act: -0.1700

Data Index: 8489886 (Open Web Text)

Max Activating Token Index: 419

Text #13

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.6008. Min Act: -0.1700

Data Index: 8620198 (Open Web Text)

Max Activating Token Index: 458

Text #14

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.5696. Min Act: -0.1700

Data Index: 4180384 (Open Web Text)

Max Activating Token Index: 528

Text #15

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.6008. Min Act: -0.1700

Data Index: 8489888 (Open Web Text)

Max Activating Token Index: 809

Text #16

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.6008. Min Act: -0.1700

Data Index: 1184524 (Open Web Text)

Max Activating Token Index: 604

Text #17

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.5696. Min Act: -0.1700

Data Index: 7517896 (Open Web Text)

Max Activating Token Index: 880

Text #18

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.6008. Min Act: -0.1700

Data Index: 5728949 (Open Web Text)

Max Activating Token Index: 1007

Text #19

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.5696. Min Act: -0.1700

Data Index: 1184527 (Open Web Text)

Max Activating Token Index: 697