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

Dataset: Open Web Text

Neuron 490 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: 5.2860. Min Range: -5.2860

Max Act: 5.2860. Min Act: -0.1700

Data Index: 2679902 (Open Web Text)

Max Activating Token Index: 639

Text #1

Max Range: 5.2860. Min Range: -5.2860

Max Act: 5.2779. Min Act: -0.1700

Data Index: 6234896 (Open Web Text)

Max Activating Token Index: 356

Text #2

Max Range: 5.2860. Min Range: -5.2860

Max Act: 5.1841. Min Act: -0.1700

Data Index: 7497003 (Open Web Text)

Max Activating Token Index: 880

Text #3

Max Range: 5.2860. Min Range: -5.2860

Max Act: 5.1309. Min Act: -0.1700

Data Index: 4664690 (Open Web Text)

Max Activating Token Index: 23

Text #4

Max Range: 5.2860. Min Range: -5.2860

Max Act: 5.1297. Min Act: -0.1700

Data Index: 550891 (Open Web Text)

Max Activating Token Index: 875

Text #5

Max Range: 5.2860. Min Range: -5.2860

Max Act: 5.1087. Min Act: -0.1700

Data Index: 4882949 (Open Web Text)

Max Activating Token Index: 314

Text #6

Max Range: 5.2860. Min Range: -5.2860

Max Act: 5.1135. Min Act: -0.1700

Data Index: 4423143 (Open Web Text)

Max Activating Token Index: 911

Text #7

Max Range: 5.2860. Min Range: -5.2860

Max Act: 5.0941. Min Act: -0.1700

Data Index: 1566057 (Open Web Text)

Max Activating Token Index: 347

Text #8

Max Range: 5.2860. Min Range: -5.2860

Max Act: 5.1126. Min Act: -0.1700

Data Index: 3203868 (Open Web Text)

Max Activating Token Index: 813

Text #9

Max Range: 5.2860. Min Range: -5.2860

Max Act: 5.0540. Min Act: -0.1700

Data Index: 1144279 (Open Web Text)

Max Activating Token Index: 574

Text #10

Max Range: 5.2860. Min Range: -5.2860

Max Act: 5.0563. Min Act: -0.1700

Data Index: 5812402 (Open Web Text)

Max Activating Token Index: 144

Text #11

Max Range: 5.2860. Min Range: -5.2860

Max Act: 5.0581. Min Act: -0.1700

Data Index: 1425859 (Open Web Text)

Max Activating Token Index: 21

Text #12

Max Range: 5.2860. Min Range: -5.2860

Max Act: 4.9997. Min Act: -0.1700

Data Index: 8147903 (Open Web Text)

Max Activating Token Index: 504

Text #13

Max Range: 5.2860. Min Range: -5.2860

Max Act: 4.9969. Min Act: -0.1700

Data Index: 5765106 (Open Web Text)

Max Activating Token Index: 152

Text #14

Max Range: 5.2860. Min Range: -5.2860

Max Act: 5.0036. Min Act: -0.1700

Data Index: 1565348 (Open Web Text)

Max Activating Token Index: 671

Text #15

Max Range: 5.2860. Min Range: -5.2860

Max Act: 4.9923. Min Act: -0.1700

Data Index: 4559336 (Open Web Text)

Max Activating Token Index: 803

Text #16

Max Range: 5.2860. Min Range: -5.2860

Max Act: 5.0027. Min Act: -0.1700

Data Index: 7069522 (Open Web Text)

Max Activating Token Index: 130

Text #17

Max Range: 5.2860. Min Range: -5.2860

Max Act: 4.9911. Min Act: -0.1700

Data Index: 2259284 (Open Web Text)

Max Activating Token Index: 131

Text #18

Max Range: 5.2860. Min Range: -5.2860

Max Act: 4.9774. Min Act: -0.1700

Data Index: 8492672 (Open Web Text)

Max Activating Token Index: 893

Text #19

Max Range: 5.2860. Min Range: -5.2860

Max Act: 4.9251. Min Act: -0.1700

Data Index: 2527106 (Open Web Text)

Max Activating Token Index: 608