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

Dataset: Open Web Text

Neuron 1549 in Layer 4

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: 4.1062. Min Range: -4.1062

Max Act: 4.1062. Min Act: -0.1700

Data Index: 2526632 (Open Web Text)

Max Activating Token Index: 443

Text #1

Max Range: 4.1062. Min Range: -4.1062

Max Act: 3.9864. Min Act: -0.1700

Data Index: 2294951 (Open Web Text)

Max Activating Token Index: 1005

Text #2

Max Range: 4.1062. Min Range: -4.1062

Max Act: 3.9772. Min Act: -0.1700

Data Index: 3042395 (Open Web Text)

Max Activating Token Index: 933

Text #3

Max Range: 4.1062. Min Range: -4.1062

Max Act: 3.9883. Min Act: -0.1700

Data Index: 6859872 (Open Web Text)

Max Activating Token Index: 840

Text #4

Max Range: 4.1062. Min Range: -4.1062

Max Act: 3.9092. Min Act: -0.1700

Data Index: 3358937 (Open Web Text)

Max Activating Token Index: 408

Text #5

Max Range: 4.1062. Min Range: -4.1062

Max Act: 3.9463. Min Act: -0.1700

Data Index: 7685332 (Open Web Text)

Max Activating Token Index: 932

Text #6

Max Range: 4.1062. Min Range: -4.1062

Max Act: 3.8577. Min Act: -0.1700

Data Index: 1550387 (Open Web Text)

Max Activating Token Index: 506

Text #7

Max Range: 4.1062. Min Range: -4.1062

Max Act: 3.8733. Min Act: -0.1700

Data Index: 1324550 (Open Web Text)

Max Activating Token Index: 180

Text #8

Max Range: 4.1062. Min Range: -4.1062

Max Act: 3.8291. Min Act: -0.1700

Data Index: 1105187 (Open Web Text)

Max Activating Token Index: 238

Text #9

Max Range: 4.1062. Min Range: -4.1062

Max Act: 3.8393. Min Act: -0.1700

Data Index: 1683644 (Open Web Text)

Max Activating Token Index: 714

Text #10

Max Range: 4.1062. Min Range: -4.1062

Max Act: 3.7971. Min Act: -0.1700

Data Index: 6385147 (Open Web Text)

Max Activating Token Index: 189

Text #11

Max Range: 4.1062. Min Range: -4.1062

Max Act: 3.8185. Min Act: -0.1700

Data Index: 946296 (Open Web Text)

Max Activating Token Index: 972

Text #12

Max Range: 4.1062. Min Range: -4.1062

Max Act: 3.8750. Min Act: -0.1700

Data Index: 6376960 (Open Web Text)

Max Activating Token Index: 774

Text #13

Max Range: 4.1062. Min Range: -4.1062

Max Act: 3.8077. Min Act: -0.1700

Data Index: 569891 (Open Web Text)

Max Activating Token Index: 858

Text #14

Max Range: 4.1062. Min Range: -4.1062

Max Act: 3.7699. Min Act: -0.1700

Data Index: 1138407 (Open Web Text)

Max Activating Token Index: 670

Text #15

Max Range: 4.1062. Min Range: -4.1062

Max Act: 3.7507. Min Act: -0.1700

Data Index: 2724853 (Open Web Text)

Max Activating Token Index: 430

Text #16

Max Range: 4.1062. Min Range: -4.1062

Max Act: 3.7301. Min Act: -0.1700

Data Index: 1369343 (Open Web Text)

Max Activating Token Index: 992

Text #17

Max Range: 4.1062. Min Range: -4.1062

Max Act: 3.7360. Min Act: -0.1700

Data Index: 1751156 (Open Web Text)

Max Activating Token Index: 908

Text #18

Max Range: 4.1062. Min Range: -4.1062

Max Act: 3.7073. Min Act: -0.1700

Data Index: 4258438 (Open Web Text)

Max Activating Token Index: 893

Text #19

Max Range: 4.1062. Min Range: -4.1062

Max Act: 3.7312. Min Act: -0.1700

Data Index: 1292245 (Open Web Text)

Max Activating Token Index: 31