Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2772 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 1.4694. Min Range: -1.4694

Max Act: 1.4694. Min Act: -0.1700

Data Index: 6816919 (Open Web Text)

Max Activating Token Index: 452

Text #1

Max Range: 1.4694. Min Range: -1.4694

Max Act: 1.4676. Min Act: -0.1700

Data Index: 1127389 (Open Web Text)

Max Activating Token Index: 361

Text #2

Max Range: 1.4694. Min Range: -1.4694

Max Act: 1.4406. Min Act: -0.1700

Data Index: 6791207 (Open Web Text)

Max Activating Token Index: 92

Text #3

Max Range: 1.4694. Min Range: -1.4694

Max Act: 1.4478. Min Act: -0.1699

Data Index: 6383358 (Open Web Text)

Max Activating Token Index: 451

Text #4

Max Range: 1.4694. Min Range: -1.4694

Max Act: 1.4426. Min Act: -0.1700

Data Index: 958292 (Open Web Text)

Max Activating Token Index: 473

Text #5

Max Range: 1.4694. Min Range: -1.4694

Max Act: 1.4334. Min Act: -0.1695

Data Index: 3854558 (Open Web Text)

Max Activating Token Index: 20

Text #6

Max Range: 1.4694. Min Range: -1.4694

Max Act: 1.4251. Min Act: -0.1700

Data Index: 4837784 (Open Web Text)

Max Activating Token Index: 291

Text #7

Max Range: 1.4694. Min Range: -1.4694

Max Act: 1.4222. Min Act: -0.1700

Data Index: 1342857 (Open Web Text)

Max Activating Token Index: 868

Text #8

Max Range: 1.4694. Min Range: -1.4694

Max Act: 1.4058. Min Act: -0.1691

Data Index: 5037336 (Open Web Text)

Max Activating Token Index: 801

Text #9

Max Range: 1.4694. Min Range: -1.4694

Max Act: 1.4069. Min Act: -0.1700

Data Index: 7770105 (Open Web Text)

Max Activating Token Index: 527

Text #10

Max Range: 1.4694. Min Range: -1.4694

Max Act: 1.4120. Min Act: -0.1700

Data Index: 5919418 (Open Web Text)

Max Activating Token Index: 381

Text #11

Max Range: 1.4694. Min Range: -1.4694

Max Act: 1.4052. Min Act: -0.1700

Data Index: 8764907 (Open Web Text)

Max Activating Token Index: 91

Text #12

Max Range: 1.4694. Min Range: -1.4694

Max Act: 1.4060. Min Act: -0.1700

Data Index: 3589181 (Open Web Text)

Max Activating Token Index: 69

Text #13

Max Range: 1.4694. Min Range: -1.4694

Max Act: 1.4090. Min Act: -0.1700

Data Index: 525338 (Open Web Text)

Max Activating Token Index: 543

Text #14

Max Range: 1.4694. Min Range: -1.4694

Max Act: 1.4078. Min Act: -0.1700

Data Index: 1250217 (Open Web Text)

Max Activating Token Index: 113

Text #15

Max Range: 1.4694. Min Range: -1.4694

Max Act: 1.4060. Min Act: -0.1700

Data Index: 5424721 (Open Web Text)

Max Activating Token Index: 222

Text #16

Max Range: 1.4694. Min Range: -1.4694

Max Act: 1.3955. Min Act: -0.1700

Data Index: 3090102 (Open Web Text)

Max Activating Token Index: 591

Text #17

Max Range: 1.4694. Min Range: -1.4694

Max Act: 1.3852. Min Act: -0.1700

Data Index: 7645505 (Open Web Text)

Max Activating Token Index: 548

Text #18

Max Range: 1.4694. Min Range: -1.4694

Max Act: 1.3847. Min Act: -0.1700

Data Index: 5644232 (Open Web Text)

Max Activating Token Index: 418

Text #19

Max Range: 1.4694. Min Range: -1.4694

Max Act: 1.3943. Min Act: -0.1699

Data Index: 7032029 (Open Web Text)

Max Activating Token Index: 202