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

Dataset: Open Web Text

Neuron 1721 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: 3.2083. Min Range: -3.2083

Max Act: 3.2083. Min Act: -0.1698

Data Index: 6801889 (Open Web Text)

Max Activating Token Index: 102

Text #1

Max Range: 3.2083. Min Range: -3.2083

Max Act: 3.1288. Min Act: -0.1700

Data Index: 3061784 (Open Web Text)

Max Activating Token Index: 52

Text #2

Max Range: 3.2083. Min Range: -3.2083

Max Act: 3.1362. Min Act: -0.1700

Data Index: 4620872 (Open Web Text)

Max Activating Token Index: 648

Text #3

Max Range: 3.2083. Min Range: -3.2083

Max Act: 3.0910. Min Act: -0.1700

Data Index: 2379293 (Open Web Text)

Max Activating Token Index: 635

Text #4

Max Range: 3.2083. Min Range: -3.2083

Max Act: 3.1009. Min Act: -0.1700

Data Index: 4683282 (Open Web Text)

Max Activating Token Index: 461

Text #5

Max Range: 3.2083. Min Range: -3.2083

Max Act: 3.0994. Min Act: -0.1700

Data Index: 1190347 (Open Web Text)

Max Activating Token Index: 253

Text #6

Max Range: 3.2083. Min Range: -3.2083

Max Act: 3.0738. Min Act: -0.1700

Data Index: 7006573 (Open Web Text)

Max Activating Token Index: 753

Text #7

Max Range: 3.2083. Min Range: -3.2083

Max Act: 3.0560. Min Act: -0.1700

Data Index: 4840811 (Open Web Text)

Max Activating Token Index: 603

Text #8

Max Range: 3.2083. Min Range: -3.2083

Max Act: 3.0522. Min Act: -0.1700

Data Index: 651549 (Open Web Text)

Max Activating Token Index: 247

Text #9

Max Range: 3.2083. Min Range: -3.2083

Max Act: 3.0580. Min Act: -0.1700

Data Index: 2767569 (Open Web Text)

Max Activating Token Index: 525

Text #10

Max Range: 3.2083. Min Range: -3.2083

Max Act: 3.0490. Min Act: -0.1700

Data Index: 6543918 (Open Web Text)

Max Activating Token Index: 552

Text #11

Max Range: 3.2083. Min Range: -3.2083

Max Act: 3.0305. Min Act: -0.1700

Data Index: 4441091 (Open Web Text)

Max Activating Token Index: 395

Text #12

Max Range: 3.2083. Min Range: -3.2083

Max Act: 3.0235. Min Act: -0.1700

Data Index: 1507704 (Open Web Text)

Max Activating Token Index: 534

Text #13

Max Range: 3.2083. Min Range: -3.2083

Max Act: 3.0211. Min Act: -0.1699

Data Index: 771085 (Open Web Text)

Max Activating Token Index: 55

Text #14

Max Range: 3.2083. Min Range: -3.2083

Max Act: 3.0258. Min Act: -0.1700

Data Index: 4564583 (Open Web Text)

Max Activating Token Index: 218

Text #15

Max Range: 3.2083. Min Range: -3.2083

Max Act: 3.0089. Min Act: -0.1700

Data Index: 3406744 (Open Web Text)

Max Activating Token Index: 174

Text #16

Max Range: 3.2083. Min Range: -3.2083

Max Act: 3.0175. Min Act: -0.1700

Data Index: 6554648 (Open Web Text)

Max Activating Token Index: 63

Text #17

Max Range: 3.2083. Min Range: -3.2083

Max Act: 2.9924. Min Act: -0.1700

Data Index: 3430586 (Open Web Text)

Max Activating Token Index: 686

Text #18

Max Range: 3.2083. Min Range: -3.2083

Max Act: 2.9974. Min Act: -0.1698

Data Index: 526714 (Open Web Text)

Max Activating Token Index: 255

Text #19

Max Range: 3.2083. Min Range: -3.2083

Max Act: 2.9903. Min Act: -0.1700

Data Index: 2767565 (Open Web Text)

Max Activating Token Index: 279