Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer

Dataset: Open Web Text

Neuron 1530 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.8320. Min Act: -0.1700

Data Index: 7521382 (Open Web Text)

Max Activating Token Index: 749

Text #1

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.8001. Min Act: -0.1700

Data Index: 5799027 (Open Web Text)

Max Activating Token Index: 952

Text #2

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.7842. Min Act: -0.1700

Data Index: 1663919 (Open Web Text)

Max Activating Token Index: 488

Text #3

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.7204. Min Act: -0.1700

Data Index: 899873 (Open Web Text)

Max Activating Token Index: 774

Text #4

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.6884. Min Act: -0.1700

Data Index: 1300750 (Open Web Text)

Max Activating Token Index: 890

Text #5

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.6884. Min Act: -0.1700

Data Index: 5760660 (Open Web Text)

Max Activating Token Index: 882

Text #6

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.6724. Min Act: -0.1700

Data Index: 7873361 (Open Web Text)

Max Activating Token Index: 481

Text #7

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.6563. Min Act: -0.1700

Data Index: 2635618 (Open Web Text)

Max Activating Token Index: 289

Text #8

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.6563. Min Act: -0.1700

Data Index: 2406140 (Open Web Text)

Max Activating Token Index: 270

Text #9

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.6403. Min Act: -0.1700

Data Index: 4457674 (Open Web Text)

Max Activating Token Index: 894

Text #10

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.6403. Min Act: -0.1700

Data Index: 507324 (Open Web Text)

Max Activating Token Index: 762

Text #11

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.6081. Min Act: -0.1700

Data Index: 4219444 (Open Web Text)

Max Activating Token Index: 496

Text #12

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.6242. Min Act: -0.1700

Data Index: 8638153 (Open Web Text)

Max Activating Token Index: 992

Text #13

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.5920. Min Act: -0.1700

Data Index: 1027974 (Open Web Text)

Max Activating Token Index: 560

Text #14

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.5598. Min Act: -0.1700

Data Index: 3889290 (Open Web Text)

Max Activating Token Index: 968

Text #15

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.5759. Min Act: -0.1700

Data Index: 1230351 (Open Web Text)

Max Activating Token Index: 469

Text #16

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.5920. Min Act: -0.1700

Data Index: 2377704 (Open Web Text)

Max Activating Token Index: 634

Text #17

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.5437. Min Act: -0.1700

Data Index: 5329289 (Open Web Text)

Max Activating Token Index: 95

Text #18

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.5759. Min Act: -0.1700

Data Index: 6025299 (Open Web Text)

Max Activating Token Index: 937

Text #19

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.5598. Min Act: -0.1700

Data Index: 6274655 (Open Web Text)

Max Activating Token Index: 732