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

Dataset: Open Web Text

Neuron 4162 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.8320. Min Act: -0.1700

Data Index: 7459686 (Open Web Text)

Max Activating Token Index: 124

Text #1

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.7695. Min Act: -0.1700

Data Index: 1958379 (Open Web Text)

Max Activating Token Index: 46

Text #2

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.6757. Min Act: -0.1700

Data Index: 7383572 (Open Web Text)

Max Activating Token Index: 86

Text #3

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.6757. Min Act: -0.1700

Data Index: 1958378 (Open Web Text)

Max Activating Token Index: 1015

Text #4

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.5507. Min Act: -0.1700

Data Index: 1271505 (Open Web Text)

Max Activating Token Index: 502

Text #5

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.5507. Min Act: -0.1700

Data Index: 2767035 (Open Web Text)

Max Activating Token Index: 568

Text #6

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.5195. Min Act: -0.1700

Data Index: 3738631 (Open Web Text)

Max Activating Token Index: 222

Text #7

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.5195. Min Act: -0.1700

Data Index: 2258676 (Open Web Text)

Max Activating Token Index: 826

Text #8

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.5195. Min Act: -0.1700

Data Index: 3363813 (Open Web Text)

Max Activating Token Index: 930

Text #9

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.4882. Min Act: -0.1700

Data Index: 894071 (Open Web Text)

Max Activating Token Index: 690

Text #10

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.4882. Min Act: -0.1700

Data Index: 8442403 (Open Web Text)

Max Activating Token Index: 336

Text #11

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.5195. Min Act: -0.1700

Data Index: 4432526 (Open Web Text)

Max Activating Token Index: 664

Text #12

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.4570. Min Act: -0.1700

Data Index: 5080113 (Open Web Text)

Max Activating Token Index: 507

Text #13

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.4570. Min Act: -0.1700

Data Index: 8550315 (Open Web Text)

Max Activating Token Index: 618

Text #14

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.4570. Min Act: -0.1700

Data Index: 7015129 (Open Web Text)

Max Activating Token Index: 756

Text #15

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.4257. Min Act: -0.1700

Data Index: 3626737 (Open Web Text)

Max Activating Token Index: 48

Text #16

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.4257. Min Act: -0.1700

Data Index: 583928 (Open Web Text)

Max Activating Token Index: 445

Text #17

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.3945. Min Act: -0.1700

Data Index: 3972452 (Open Web Text)

Max Activating Token Index: 766

Text #18

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.4257. Min Act: -0.1700

Data Index: 1629851 (Open Web Text)

Max Activating Token Index: 533

Text #19

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.4257. Min Act: -0.1700

Data Index: 495698 (Open Web Text)

Max Activating Token Index: 40