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

Dataset: Open Web Text

Neuron 1498 in Layer 5

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: 4.0137. Min Range: -4.0137

Max Act: 4.0137. Min Act: -0.1700

Data Index: 2239657 (Open Web Text)

Max Activating Token Index: 232

Text #1

Max Range: 4.0137. Min Range: -4.0137

Max Act: 3.9537. Min Act: -0.1700

Data Index: 1394605 (Open Web Text)

Max Activating Token Index: 497

Text #2

Max Range: 4.0137. Min Range: -4.0137

Max Act: 3.9458. Min Act: -0.1700

Data Index: 4143868 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 4.0137. Min Range: -4.0137

Max Act: 3.8896. Min Act: -0.1700

Data Index: 2994509 (Open Web Text)

Max Activating Token Index: 494

Text #4

Max Range: 4.0137. Min Range: -4.0137

Max Act: 3.8977. Min Act: -0.1700

Data Index: 6843241 (Open Web Text)

Max Activating Token Index: 161

Text #5

Max Range: 4.0137. Min Range: -4.0137

Max Act: 3.8823. Min Act: -0.1700

Data Index: 3470155 (Open Web Text)

Max Activating Token Index: 12

Text #6

Max Range: 4.0137. Min Range: -4.0137

Max Act: 3.8611. Min Act: -0.1700

Data Index: 7299354 (Open Web Text)

Max Activating Token Index: 29

Text #7

Max Range: 4.0137. Min Range: -4.0137

Max Act: 3.8375. Min Act: -0.1700

Data Index: 7097955 (Open Web Text)

Max Activating Token Index: 595

Text #8

Max Range: 4.0137. Min Range: -4.0137

Max Act: 3.8749. Min Act: -0.1700

Data Index: 8442668 (Open Web Text)

Max Activating Token Index: 972

Text #9

Max Range: 4.0137. Min Range: -4.0137

Max Act: 3.8196. Min Act: -0.1700

Data Index: 2730631 (Open Web Text)

Max Activating Token Index: 122

Text #10

Max Range: 4.0137. Min Range: -4.0137

Max Act: 3.8109. Min Act: -0.1700

Data Index: 6444848 (Open Web Text)

Max Activating Token Index: 509

Text #11

Max Range: 4.0137. Min Range: -4.0137

Max Act: 3.7891. Min Act: -0.1700

Data Index: 4142345 (Open Web Text)

Max Activating Token Index: 238

Text #12

Max Range: 4.0137. Min Range: -4.0137

Max Act: 3.8024. Min Act: -0.1700

Data Index: 1144691 (Open Web Text)

Max Activating Token Index: 63

Text #13

Max Range: 4.0137. Min Range: -4.0137

Max Act: 3.7672. Min Act: -0.1700

Data Index: 29028 (Open Web Text)

Max Activating Token Index: 633

Text #14

Max Range: 4.0137. Min Range: -4.0137

Max Act: 3.7643. Min Act: -0.1700

Data Index: 1942876 (Open Web Text)

Max Activating Token Index: 9

Text #15

Max Range: 4.0137. Min Range: -4.0137

Max Act: 3.7350. Min Act: -0.1700

Data Index: 4229482 (Open Web Text)

Max Activating Token Index: 269

Text #16

Max Range: 4.0137. Min Range: -4.0137

Max Act: 3.7126. Min Act: -0.1700

Data Index: 3141687 (Open Web Text)

Max Activating Token Index: 458

Text #17

Max Range: 4.0137. Min Range: -4.0137

Max Act: 3.7295. Min Act: -0.1700

Data Index: 7299343 (Open Web Text)

Max Activating Token Index: 563

Text #18

Max Range: 4.0137. Min Range: -4.0137

Max Act: 3.7634. Min Act: -0.1700

Data Index: 1534897 (Open Web Text)

Max Activating Token Index: 389

Text #19

Max Range: 4.0137. Min Range: -4.0137

Max Act: 3.7572. Min Act: -0.1700

Data Index: 4220510 (Open Web Text)

Max Activating Token Index: 715