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

Dataset: Open Web Text

Neuron 1581 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: 3.0695. Min Range: -3.0695

Max Act: 3.0695. Min Act: -0.1700

Data Index: 4438325 (Open Web Text)

Max Activating Token Index: 736

Text #1

Max Range: 3.0695. Min Range: -3.0695

Max Act: 3.0582. Min Act: -0.1700

Data Index: 7956131 (Open Web Text)

Max Activating Token Index: 315

Text #2

Max Range: 3.0695. Min Range: -3.0695

Max Act: 3.0431. Min Act: -0.1700

Data Index: 4473019 (Open Web Text)

Max Activating Token Index: 909

Text #3

Max Range: 3.0695. Min Range: -3.0695

Max Act: 3.0377. Min Act: -0.1700

Data Index: 250804 (Open Web Text)

Max Activating Token Index: 458

Text #4

Max Range: 3.0695. Min Range: -3.0695

Max Act: 3.0195. Min Act: -0.1700

Data Index: 6243559 (Open Web Text)

Max Activating Token Index: 523

Text #5

Max Range: 3.0695. Min Range: -3.0695

Max Act: 3.0147. Min Act: -0.1700

Data Index: 191375 (Open Web Text)

Max Activating Token Index: 419

Text #6

Max Range: 3.0695. Min Range: -3.0695

Max Act: 3.0193. Min Act: -0.1700

Data Index: 3589055 (Open Web Text)

Max Activating Token Index: 391

Text #7

Max Range: 3.0695. Min Range: -3.0695

Max Act: 3.0242. Min Act: -0.1700

Data Index: 4125929 (Open Web Text)

Max Activating Token Index: 464

Text #8

Max Range: 3.0695. Min Range: -3.0695

Max Act: 3.0027. Min Act: -0.1700

Data Index: 1317862 (Open Web Text)

Max Activating Token Index: 563

Text #9

Max Range: 3.0695. Min Range: -3.0695

Max Act: 3.0111. Min Act: -0.1700

Data Index: 8380395 (Open Web Text)

Max Activating Token Index: 548

Text #10

Max Range: 3.0695. Min Range: -3.0695

Max Act: 2.9997. Min Act: -0.1700

Data Index: 5450129 (Open Web Text)

Max Activating Token Index: 568

Text #11

Max Range: 3.0695. Min Range: -3.0695

Max Act: 2.9987. Min Act: -0.1700

Data Index: 6932110 (Open Web Text)

Max Activating Token Index: 559

Text #12

Max Range: 3.0695. Min Range: -3.0695

Max Act: 2.9913. Min Act: -0.1700

Data Index: 1504416 (Open Web Text)

Max Activating Token Index: 344

Text #13

Max Range: 3.0695. Min Range: -3.0695

Max Act: 2.9935. Min Act: -0.1700

Data Index: 5307200 (Open Web Text)

Max Activating Token Index: 771

Text #14

Max Range: 3.0695. Min Range: -3.0695

Max Act: 2.9934. Min Act: -0.1700

Data Index: 3347007 (Open Web Text)

Max Activating Token Index: 437

Text #15

Max Range: 3.0695. Min Range: -3.0695

Max Act: 2.9874. Min Act: -0.1700

Data Index: 4953327 (Open Web Text)

Max Activating Token Index: 169

Text #16

Max Range: 3.0695. Min Range: -3.0695

Max Act: 2.9924. Min Act: -0.1700

Data Index: 2866342 (Open Web Text)

Max Activating Token Index: 325

Text #17

Max Range: 3.0695. Min Range: -3.0695

Max Act: 2.9801. Min Act: -0.1700

Data Index: 8061523 (Open Web Text)

Max Activating Token Index: 365

Text #18

Max Range: 3.0695. Min Range: -3.0695

Max Act: 2.9849. Min Act: -0.1700

Data Index: 2886184 (Open Web Text)

Max Activating Token Index: 686

Text #19

Max Range: 3.0695. Min Range: -3.0695

Max Act: 2.9905. Min Act: -0.1700

Data Index: 8636558 (Open Web Text)

Max Activating Token Index: 483