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

Dataset: Open Web Text

Neuron 806 in Layer 1

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: 1.8410. Min Range: -1.8410

Max Act: 1.8410. Min Act: -0.1700

Data Index: 2531901 (Open Web Text)

Max Activating Token Index: 73

Text #1

Max Range: 1.8410. Min Range: -1.8410

Max Act: 1.7905. Min Act: -0.1700

Data Index: 7386210 (Open Web Text)

Max Activating Token Index: 925

Text #2

Max Range: 1.8410. Min Range: -1.8410

Max Act: 1.7379. Min Act: -0.1700

Data Index: 8314438 (Open Web Text)

Max Activating Token Index: 750

Text #3

Max Range: 1.8410. Min Range: -1.8410

Max Act: 1.7385. Min Act: -0.1700

Data Index: 5321360 (Open Web Text)

Max Activating Token Index: 660

Text #4

Max Range: 1.8410. Min Range: -1.8410

Max Act: 1.7288. Min Act: -0.1700

Data Index: 4646112 (Open Web Text)

Max Activating Token Index: 699

Text #5

Max Range: 1.8410. Min Range: -1.8410

Max Act: 1.7308. Min Act: -0.1700

Data Index: 1908562 (Open Web Text)

Max Activating Token Index: 142

Text #6

Max Range: 1.8410. Min Range: -1.8410

Max Act: 1.7246. Min Act: -0.1700

Data Index: 1787907 (Open Web Text)

Max Activating Token Index: 719

Text #7

Max Range: 1.8410. Min Range: -1.8410

Max Act: 1.7214. Min Act: -0.1700

Data Index: 7607405 (Open Web Text)

Max Activating Token Index: 727

Text #8

Max Range: 1.8410. Min Range: -1.8410

Max Act: 1.7162. Min Act: -0.1700

Data Index: 3316177 (Open Web Text)

Max Activating Token Index: 62

Text #9

Max Range: 1.8410. Min Range: -1.8410

Max Act: 1.7064. Min Act: -0.1700

Data Index: 4736097 (Open Web Text)

Max Activating Token Index: 955

Text #10

Max Range: 1.8410. Min Range: -1.8410

Max Act: 1.7051. Min Act: -0.1700

Data Index: 6260807 (Open Web Text)

Max Activating Token Index: 578

Text #11

Max Range: 1.8410. Min Range: -1.8410

Max Act: 1.7035. Min Act: -0.1700

Data Index: 5176666 (Open Web Text)

Max Activating Token Index: 642

Text #12

Max Range: 1.8410. Min Range: -1.8410

Max Act: 1.7146. Min Act: -0.1700

Data Index: 2531897 (Open Web Text)

Max Activating Token Index: 309

Text #13

Max Range: 1.8410. Min Range: -1.8410

Max Act: 1.7093. Min Act: -0.1700

Data Index: 7915210 (Open Web Text)

Max Activating Token Index: 545

Text #14

Max Range: 1.8410. Min Range: -1.8410

Max Act: 1.7129. Min Act: -0.1700

Data Index: 4893954 (Open Web Text)

Max Activating Token Index: 758

Text #15

Max Range: 1.8410. Min Range: -1.8410

Max Act: 1.6865. Min Act: -0.1700

Data Index: 8686002 (Open Web Text)

Max Activating Token Index: 424

Text #16

Max Range: 1.8410. Min Range: -1.8410

Max Act: 1.6956. Min Act: -0.1700

Data Index: 3636523 (Open Web Text)

Max Activating Token Index: 748

Text #17

Max Range: 1.8410. Min Range: -1.8410

Max Act: 1.6937. Min Act: -0.1700

Data Index: 4438081 (Open Web Text)

Max Activating Token Index: 155

Text #18

Max Range: 1.8410. Min Range: -1.8410

Max Act: 1.6904. Min Act: -0.1700

Data Index: 1847429 (Open Web Text)

Max Activating Token Index: 448

Text #19

Max Range: 1.8410. Min Range: -1.8410

Max Act: 1.6847. Min Act: -0.1700

Data Index: 2579335 (Open Web Text)

Max Activating Token Index: 660