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

Dataset: Open Web Text

Neuron 2811 in Layer 37

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.8320. Min Range: -7.8320

Max Act: 7.8320. Min Act: -0.1700

Data Index: 6596459 (Open Web Text)

Max Activating Token Index: 639

Text #1

Max Range: 7.8320. Min Range: -7.8320

Max Act: 7.7695. Min Act: -0.1700

Data Index: 3083787 (Open Web Text)

Max Activating Token Index: 475

Text #2

Max Range: 7.8320. Min Range: -7.8320

Max Act: 7.6445. Min Act: -0.1700

Data Index: 6788390 (Open Web Text)

Max Activating Token Index: 493

Text #3

Max Range: 7.8320. Min Range: -7.8320

Max Act: 7.5195. Min Act: -0.1700

Data Index: 1999160 (Open Web Text)

Max Activating Token Index: 666

Text #4

Max Range: 7.8320. Min Range: -7.8320

Max Act: 7.4570. Min Act: -0.1700

Data Index: 7817545 (Open Web Text)

Max Activating Token Index: 648

Text #5

Max Range: 7.8320. Min Range: -7.8320

Max Act: 7.4257. Min Act: -0.1700

Data Index: 334969 (Open Web Text)

Max Activating Token Index: 505

Text #6

Max Range: 7.8320. Min Range: -7.8320

Max Act: 7.3945. Min Act: -0.1700

Data Index: 5121025 (Open Web Text)

Max Activating Token Index: 286

Text #7

Max Range: 7.8320. Min Range: -7.8320

Max Act: 7.3945. Min Act: -0.1700

Data Index: 4492916 (Open Web Text)

Max Activating Token Index: 361

Text #8

Max Range: 7.8320. Min Range: -7.8320

Max Act: 7.3945. Min Act: -0.1700

Data Index: 5854628 (Open Web Text)

Max Activating Token Index: 222

Text #9

Max Range: 7.8320. Min Range: -7.8320

Max Act: 7.3632. Min Act: -0.1700

Data Index: 364285 (Open Web Text)

Max Activating Token Index: 314

Text #10

Max Range: 7.8320. Min Range: -7.8320

Max Act: 7.3632. Min Act: -0.1700

Data Index: 5284060 (Open Web Text)

Max Activating Token Index: 493

Text #11

Max Range: 7.8320. Min Range: -7.8320

Max Act: 7.3632. Min Act: -0.1700

Data Index: 1894843 (Open Web Text)

Max Activating Token Index: 745

Text #12

Max Range: 7.8320. Min Range: -7.8320

Max Act: 7.3320. Min Act: -0.1700

Data Index: 4848168 (Open Web Text)

Max Activating Token Index: 896

Text #13

Max Range: 7.8320. Min Range: -7.8320

Max Act: 7.3320. Min Act: -0.1700

Data Index: 8751780 (Open Web Text)

Max Activating Token Index: 832

Text #14

Max Range: 7.8320. Min Range: -7.8320

Max Act: 7.3320. Min Act: -0.1700

Data Index: 5039892 (Open Web Text)

Max Activating Token Index: 432

Text #15

Max Range: 7.8320. Min Range: -7.8320

Max Act: 7.3320. Min Act: -0.1700

Data Index: 463798 (Open Web Text)

Max Activating Token Index: 212

Text #16

Max Range: 7.8320. Min Range: -7.8320

Max Act: 7.3007. Min Act: -0.1700

Data Index: 7183827 (Open Web Text)

Max Activating Token Index: 182

Text #17

Max Range: 7.8320. Min Range: -7.8320

Max Act: 7.2695. Min Act: -0.1700

Data Index: 7408378 (Open Web Text)

Max Activating Token Index: 561

Text #18

Max Range: 7.8320. Min Range: -7.8320

Max Act: 7.2695. Min Act: -0.1700

Data Index: 3565447 (Open Web Text)

Max Activating Token Index: 724

Text #19

Max Range: 7.8320. Min Range: -7.8320

Max Act: 7.2695. Min Act: -0.1700

Data Index: 5390315 (Open Web Text)

Max Activating Token Index: 217