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

Dataset: Open Web Text

Neuron 5481 in Layer 42

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 10.1109. Min Range: -10.1109

Max Act: 10.1109. Min Act: -0.1700

Data Index: 8034846 (Open Web Text)

Max Activating Token Index: 256

Text #1

Max Range: 10.1109. Min Range: -10.1109

Max Act: 9.7984. Min Act: -0.1700

Data Index: 262731 (Open Web Text)

Max Activating Token Index: 501

Text #2

Max Range: 10.1109. Min Range: -10.1109

Max Act: 9.7359. Min Act: -0.1700

Data Index: 2102072 (Open Web Text)

Max Activating Token Index: 713

Text #3

Max Range: 10.1109. Min Range: -10.1109

Max Act: 9.6734. Min Act: -0.1700

Data Index: 6703236 (Open Web Text)

Max Activating Token Index: 326

Text #4

Max Range: 10.1109. Min Range: -10.1109

Max Act: 9.5484. Min Act: -0.1700

Data Index: 1174723 (Open Web Text)

Max Activating Token Index: 218

Text #5

Max Range: 10.1109. Min Range: -10.1109

Max Act: 9.4859. Min Act: -0.1700

Data Index: 2216331 (Open Web Text)

Max Activating Token Index: 434

Text #6

Max Range: 10.1109. Min Range: -10.1109

Max Act: 9.4234. Min Act: -0.1700

Data Index: 4980263 (Open Web Text)

Max Activating Token Index: 985

Text #7

Max Range: 10.1109. Min Range: -10.1109

Max Act: 9.4234. Min Act: -0.1700

Data Index: 262732 (Open Web Text)

Max Activating Token Index: 925

Text #8

Max Range: 10.1109. Min Range: -10.1109

Max Act: 9.4234. Min Act: -0.1700

Data Index: 6280489 (Open Web Text)

Max Activating Token Index: 242

Text #9

Max Range: 10.1109. Min Range: -10.1109

Max Act: 9.4234. Min Act: -0.1700

Data Index: 91025 (Open Web Text)

Max Activating Token Index: 386

Text #10

Max Range: 10.1109. Min Range: -10.1109

Max Act: 9.3609. Min Act: -0.1700

Data Index: 6753614 (Open Web Text)

Max Activating Token Index: 738

Text #11

Max Range: 10.1109. Min Range: -10.1109

Max Act: 9.3609. Min Act: -0.1700

Data Index: 2268558 (Open Web Text)

Max Activating Token Index: 714

Text #12

Max Range: 10.1109. Min Range: -10.1109

Max Act: 9.3609. Min Act: -0.1700

Data Index: 2855806 (Open Web Text)

Max Activating Token Index: 106

Text #13

Max Range: 10.1109. Min Range: -10.1109

Max Act: 9.3609. Min Act: -0.1700

Data Index: 2750931 (Open Web Text)

Max Activating Token Index: 871

Text #14

Max Range: 10.1109. Min Range: -10.1109

Max Act: 9.3609. Min Act: -0.1700

Data Index: 8410516 (Open Web Text)

Max Activating Token Index: 555

Text #15

Max Range: 10.1109. Min Range: -10.1109

Max Act: 9.3609. Min Act: -0.1700

Data Index: 4083293 (Open Web Text)

Max Activating Token Index: 361

Text #16

Max Range: 10.1109. Min Range: -10.1109

Max Act: 9.2984. Min Act: -0.1700

Data Index: 626416 (Open Web Text)

Max Activating Token Index: 518

Text #17

Max Range: 10.1109. Min Range: -10.1109

Max Act: 9.2984. Min Act: -0.1700

Data Index: 3312158 (Open Web Text)

Max Activating Token Index: 286

Text #18

Max Range: 10.1109. Min Range: -10.1109

Max Act: 9.2984. Min Act: -0.1700

Data Index: 5452041 (Open Web Text)

Max Activating Token Index: 421

Text #19

Max Range: 10.1109. Min Range: -10.1109

Max Act: 9.2984. Min Act: -0.1700

Data Index: 2478948 (Open Web Text)

Max Activating Token Index: 644