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

Dataset: Open Web Text

Neuron 871 in Layer 22

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.1016. Min Range: -6.1016

Max Act: 6.1016. Min Act: -0.1700

Data Index: 1272275 (Open Web Text)

Max Activating Token Index: 301

Text #1

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.9766. Min Act: -0.1700

Data Index: 4619371 (Open Web Text)

Max Activating Token Index: 303

Text #2

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.9453. Min Act: -0.1700

Data Index: 2709672 (Open Web Text)

Max Activating Token Index: 194

Text #3

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.8828. Min Act: -0.1700

Data Index: 8708895 (Open Web Text)

Max Activating Token Index: 300

Text #4

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.9141. Min Act: -0.1700

Data Index: 567610 (Open Web Text)

Max Activating Token Index: 265

Text #5

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.8516. Min Act: -0.1700

Data Index: 6899363 (Open Web Text)

Max Activating Token Index: 134

Text #6

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.7578. Min Act: -0.1700

Data Index: 145933 (Open Web Text)

Max Activating Token Index: 167

Text #7

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.7266. Min Act: -0.1700

Data Index: 5061108 (Open Web Text)

Max Activating Token Index: 512

Text #8

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.7266. Min Act: -0.1700

Data Index: 8230478 (Open Web Text)

Max Activating Token Index: 141

Text #9

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.6953. Min Act: -0.1700

Data Index: 5742863 (Open Web Text)

Max Activating Token Index: 479

Text #10

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.6953. Min Act: -0.1700

Data Index: 8596826 (Open Web Text)

Max Activating Token Index: 434

Text #11

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.6328. Min Act: -0.1700

Data Index: 617390 (Open Web Text)

Max Activating Token Index: 882

Text #12

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.6016. Min Act: -0.1700

Data Index: 3682380 (Open Web Text)

Max Activating Token Index: 597

Text #13

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.6016. Min Act: -0.1700

Data Index: 3961689 (Open Web Text)

Max Activating Token Index: 517

Text #14

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.6016. Min Act: -0.1700

Data Index: 1273370 (Open Web Text)

Max Activating Token Index: 446

Text #15

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.5391. Min Act: -0.1700

Data Index: 2958109 (Open Web Text)

Max Activating Token Index: 438

Text #16

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.5703. Min Act: -0.1700

Data Index: 8536533 (Open Web Text)

Max Activating Token Index: 111

Text #17

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.5703. Min Act: -0.1700

Data Index: 1466414 (Open Web Text)

Max Activating Token Index: 226

Text #18

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.5703. Min Act: -0.1700

Data Index: 6050875 (Open Web Text)

Max Activating Token Index: 906

Text #19

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.5391. Min Act: -0.1700

Data Index: 7502837 (Open Web Text)

Max Activating Token Index: 165