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

Dataset: Open Web Text

Neuron 6326 in Layer 45

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 10.8320. Min Range: -10.8320

Max Act: 10.8320. Min Act: -0.1700

Data Index: 5230036 (Open Web Text)

Max Activating Token Index: 684

Text #1

Max Range: 10.8320. Min Range: -10.8320

Max Act: 10.5820. Min Act: -0.1700

Data Index: 1228607 (Open Web Text)

Max Activating Token Index: 996

Text #2

Max Range: 10.8320. Min Range: -10.8320

Max Act: 9.9570. Min Act: -0.1700

Data Index: 6871222 (Open Web Text)

Max Activating Token Index: 171

Text #3

Max Range: 10.8320. Min Range: -10.8320

Max Act: 9.9570. Min Act: -0.1700

Data Index: 5055030 (Open Web Text)

Max Activating Token Index: 147

Text #4

Max Range: 10.8320. Min Range: -10.8320

Max Act: 9.8320. Min Act: -0.1700

Data Index: 7481310 (Open Web Text)

Max Activating Token Index: 627

Text #5

Max Range: 10.8320. Min Range: -10.8320

Max Act: 9.7695. Min Act: -0.1700

Data Index: 1950735 (Open Web Text)

Max Activating Token Index: 543

Text #6

Max Range: 10.8320. Min Range: -10.8320

Max Act: 9.7695. Min Act: -0.1700

Data Index: 8582246 (Open Web Text)

Max Activating Token Index: 260

Text #7

Max Range: 10.8320. Min Range: -10.8320

Max Act: 9.7070. Min Act: -0.1700

Data Index: 3602180 (Open Web Text)

Max Activating Token Index: 787

Text #8

Max Range: 10.8320. Min Range: -10.8320

Max Act: 9.7070. Min Act: -0.1700

Data Index: 507093 (Open Web Text)

Max Activating Token Index: 710

Text #9

Max Range: 10.8320. Min Range: -10.8320

Max Act: 9.7070. Min Act: -0.1700

Data Index: 6168185 (Open Web Text)

Max Activating Token Index: 504

Text #10

Max Range: 10.8320. Min Range: -10.8320

Max Act: 9.7070. Min Act: -0.1700

Data Index: 5168274 (Open Web Text)

Max Activating Token Index: 395

Text #11

Max Range: 10.8320. Min Range: -10.8320

Max Act: 9.7070. Min Act: -0.1700

Data Index: 7402734 (Open Web Text)

Max Activating Token Index: 956

Text #12

Max Range: 10.8320. Min Range: -10.8320

Max Act: 9.7695. Min Act: -0.1700

Data Index: 3408169 (Open Web Text)

Max Activating Token Index: 655

Text #13

Max Range: 10.8320. Min Range: -10.8320

Max Act: 9.6445. Min Act: -0.1700

Data Index: 8582245 (Open Web Text)

Max Activating Token Index: 492

Text #14

Max Range: 10.8320. Min Range: -10.8320

Max Act: 9.6445. Min Act: -0.1700

Data Index: 3408170 (Open Web Text)

Max Activating Token Index: 424

Text #15

Max Range: 10.8320. Min Range: -10.8320

Max Act: 9.6445. Min Act: -0.1700

Data Index: 2929026 (Open Web Text)

Max Activating Token Index: 886

Text #16

Max Range: 10.8320. Min Range: -10.8320

Max Act: 9.6445. Min Act: -0.1700

Data Index: 7088558 (Open Web Text)

Max Activating Token Index: 882

Text #17

Max Range: 10.8320. Min Range: -10.8320

Max Act: 9.6445. Min Act: -0.1700

Data Index: 98353 (Open Web Text)

Max Activating Token Index: 843

Text #18

Max Range: 10.8320. Min Range: -10.8320

Max Act: 9.6445. Min Act: -0.1700

Data Index: 2262164 (Open Web Text)

Max Activating Token Index: 799

Text #19

Max Range: 10.8320. Min Range: -10.8320

Max Act: 9.6445. Min Act: -0.1700

Data Index: 6871221 (Open Web Text)

Max Activating Token Index: 403