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

Dataset: Open Web Text

Neuron 2297 in Layer 6

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: 4.3838. Min Range: -4.3838

Max Act: 4.3838. Min Act: -0.1700

Data Index: 2293834 (Open Web Text)

Max Activating Token Index: 549

Text #1

Max Range: 4.3838. Min Range: -4.3838

Max Act: 4.3223. Min Act: -0.1700

Data Index: 501143 (Open Web Text)

Max Activating Token Index: 847

Text #2

Max Range: 4.3838. Min Range: -4.3838

Max Act: 4.2976. Min Act: -0.1700

Data Index: 5136213 (Open Web Text)

Max Activating Token Index: 668

Text #3

Max Range: 4.3838. Min Range: -4.3838

Max Act: 4.3106. Min Act: -0.1700

Data Index: 8567874 (Open Web Text)

Max Activating Token Index: 227

Text #4

Max Range: 4.3838. Min Range: -4.3838

Max Act: 4.2940. Min Act: -0.1700

Data Index: 4119240 (Open Web Text)

Max Activating Token Index: 890

Text #5

Max Range: 4.3838. Min Range: -4.3838

Max Act: 4.2709. Min Act: -0.1700

Data Index: 790093 (Open Web Text)

Max Activating Token Index: 319

Text #6

Max Range: 4.3838. Min Range: -4.3838

Max Act: 4.2354. Min Act: -0.1700

Data Index: 6146776 (Open Web Text)

Max Activating Token Index: 970

Text #7

Max Range: 4.3838. Min Range: -4.3838

Max Act: 4.2269. Min Act: -0.1700

Data Index: 1312015 (Open Web Text)

Max Activating Token Index: 386

Text #8

Max Range: 4.3838. Min Range: -4.3838

Max Act: 4.2020. Min Act: -0.1700

Data Index: 790092 (Open Web Text)

Max Activating Token Index: 761

Text #9

Max Range: 4.3838. Min Range: -4.3838

Max Act: 4.1720. Min Act: -0.1700

Data Index: 9585 (Open Web Text)

Max Activating Token Index: 113

Text #10

Max Range: 4.3838. Min Range: -4.3838

Max Act: 4.1554. Min Act: -0.1700

Data Index: 2630926 (Open Web Text)

Max Activating Token Index: 753

Text #11

Max Range: 4.3838. Min Range: -4.3838

Max Act: 4.1623. Min Act: -0.1700

Data Index: 5136212 (Open Web Text)

Max Activating Token Index: 777

Text #12

Max Range: 4.3838. Min Range: -4.3838

Max Act: 4.1300. Min Act: -0.1700

Data Index: 7443398 (Open Web Text)

Max Activating Token Index: 460

Text #13

Max Range: 4.3838. Min Range: -4.3838

Max Act: 4.0923. Min Act: -0.1700

Data Index: 693515 (Open Web Text)

Max Activating Token Index: 908

Text #14

Max Range: 4.3838. Min Range: -4.3838

Max Act: 4.0873. Min Act: -0.1700

Data Index: 2258520 (Open Web Text)

Max Activating Token Index: 907

Text #15

Max Range: 4.3838. Min Range: -4.3838

Max Act: 4.1449. Min Act: -0.1700

Data Index: 1536370 (Open Web Text)

Max Activating Token Index: 564

Text #16

Max Range: 4.3838. Min Range: -4.3838

Max Act: 4.1403. Min Act: -0.1700

Data Index: 1077849 (Open Web Text)

Max Activating Token Index: 121

Text #17

Max Range: 4.3838. Min Range: -4.3838

Max Act: 4.1093. Min Act: -0.1700

Data Index: 5428461 (Open Web Text)

Max Activating Token Index: 773

Text #18

Max Range: 4.3838. Min Range: -4.3838

Max Act: 4.1024. Min Act: -0.1700

Data Index: 383149 (Open Web Text)

Max Activating Token Index: 780

Text #19

Max Range: 4.3838. Min Range: -4.3838

Max Act: 4.0783. Min Act: -0.1700

Data Index: 3719751 (Open Web Text)

Max Activating Token Index: 1006