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

Dataset: Open Web Text

Neuron 422 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: 0.9441. Min Range: -0.9441

Max Act: 0.9441. Min Act: -0.1700

Data Index: 6232304 (Open Web Text)

Max Activating Token Index: 644

Text #1

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.8710. Min Act: -0.1700

Data Index: 5807153 (Open Web Text)

Max Activating Token Index: 650

Text #2

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.8691. Min Act: -0.1700

Data Index: 8445977 (Open Web Text)

Max Activating Token Index: 651

Text #3

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.8606. Min Act: -0.1700

Data Index: 1184662 (Open Web Text)

Max Activating Token Index: 640

Text #4

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.8293. Min Act: -0.1700

Data Index: 1509103 (Open Web Text)

Max Activating Token Index: 662

Text #5

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.8326. Min Act: -0.1700

Data Index: 1245377 (Open Web Text)

Max Activating Token Index: 676

Text #6

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.8321. Min Act: -0.1700

Data Index: 4259401 (Open Web Text)

Max Activating Token Index: 666

Text #7

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.8184. Min Act: -0.1700

Data Index: 2025094 (Open Web Text)

Max Activating Token Index: 632

Text #8

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.8084. Min Act: -0.1700

Data Index: 4637340 (Open Web Text)

Max Activating Token Index: 663

Text #9

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.8143. Min Act: -0.1700

Data Index: 2880926 (Open Web Text)

Max Activating Token Index: 659

Text #10

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.8088. Min Act: -0.1700

Data Index: 6824339 (Open Web Text)

Max Activating Token Index: 654

Text #11

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.8071. Min Act: -0.1700

Data Index: 3176210 (Open Web Text)

Max Activating Token Index: 653

Text #12

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.8129. Min Act: -0.1700

Data Index: 3395547 (Open Web Text)

Max Activating Token Index: 655

Text #13

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.8117. Min Act: -0.1700

Data Index: 2424287 (Open Web Text)

Max Activating Token Index: 653

Text #14

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.8106. Min Act: -0.1700

Data Index: 5030004 (Open Web Text)

Max Activating Token Index: 632

Text #15

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.8114. Min Act: -0.1700

Data Index: 6880812 (Open Web Text)

Max Activating Token Index: 653

Text #16

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.8083. Min Act: -0.1700

Data Index: 1129580 (Open Web Text)

Max Activating Token Index: 649

Text #17

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.8103. Min Act: -0.1700

Data Index: 7609343 (Open Web Text)

Max Activating Token Index: 637

Text #18

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.8082. Min Act: -0.1700

Data Index: 943092 (Open Web Text)

Max Activating Token Index: 624

Text #19

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.8124. Min Act: -0.1700

Data Index: 2173418 (Open Web Text)

Max Activating Token Index: 649