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

Dataset: Open Web Text

Neuron 2661 in Layer 5

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: 4.7491. Min Range: -4.7491

Max Act: 4.7491. Min Act: -0.1700

Data Index: 3065469 (Open Web Text)

Max Activating Token Index: 361

Text #1

Max Range: 4.7491. Min Range: -4.7491

Max Act: 4.7066. Min Act: -0.1700

Data Index: 3527811 (Open Web Text)

Max Activating Token Index: 569

Text #2

Max Range: 4.7491. Min Range: -4.7491

Max Act: 4.6666. Min Act: -0.1700

Data Index: 5544347 (Open Web Text)

Max Activating Token Index: 599

Text #3

Max Range: 4.7491. Min Range: -4.7491

Max Act: 4.6703. Min Act: -0.1700

Data Index: 6468578 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.7491. Min Range: -4.7491

Max Act: 4.6488. Min Act: -0.1700

Data Index: 7117123 (Open Web Text)

Max Activating Token Index: 553

Text #5

Max Range: 4.7491. Min Range: -4.7491

Max Act: 4.6432. Min Act: -0.1700

Data Index: 981297 (Open Web Text)

Max Activating Token Index: 928

Text #6

Max Range: 4.7491. Min Range: -4.7491

Max Act: 4.5807. Min Act: -0.1700

Data Index: 6892821 (Open Web Text)

Max Activating Token Index: 108

Text #7

Max Range: 4.7491. Min Range: -4.7491

Max Act: 4.5909. Min Act: -0.1700

Data Index: 6907147 (Open Web Text)

Max Activating Token Index: 313

Text #8

Max Range: 4.7491. Min Range: -4.7491

Max Act: 4.5534. Min Act: -0.1700

Data Index: 1497791 (Open Web Text)

Max Activating Token Index: 538

Text #9

Max Range: 4.7491. Min Range: -4.7491

Max Act: 4.5604. Min Act: -0.1700

Data Index: 2570196 (Open Web Text)

Max Activating Token Index: 670

Text #10

Max Range: 4.7491. Min Range: -4.7491

Max Act: 4.5603. Min Act: -0.1700

Data Index: 1234834 (Open Web Text)

Max Activating Token Index: 753

Text #11

Max Range: 4.7491. Min Range: -4.7491

Max Act: 4.5522. Min Act: -0.1700

Data Index: 8543372 (Open Web Text)

Max Activating Token Index: 895

Text #12

Max Range: 4.7491. Min Range: -4.7491

Max Act: 4.5308. Min Act: -0.1700

Data Index: 8287699 (Open Web Text)

Max Activating Token Index: 213

Text #13

Max Range: 4.7491. Min Range: -4.7491

Max Act: 4.5300. Min Act: -0.1700

Data Index: 3841635 (Open Web Text)

Max Activating Token Index: 883

Text #14

Max Range: 4.7491. Min Range: -4.7491

Max Act: 4.5317. Min Act: -0.1700

Data Index: 5992965 (Open Web Text)

Max Activating Token Index: 156

Text #15

Max Range: 4.7491. Min Range: -4.7491

Max Act: 4.5283. Min Act: -0.1700

Data Index: 4160906 (Open Web Text)

Max Activating Token Index: 536

Text #16

Max Range: 4.7491. Min Range: -4.7491

Max Act: 4.5020. Min Act: -0.1700

Data Index: 1930690 (Open Web Text)

Max Activating Token Index: 82

Text #17

Max Range: 4.7491. Min Range: -4.7491

Max Act: 4.4964. Min Act: -0.1700

Data Index: 1193326 (Open Web Text)

Max Activating Token Index: 868

Text #18

Max Range: 4.7491. Min Range: -4.7491

Max Act: 4.4718. Min Act: -0.1700

Data Index: 2990682 (Open Web Text)

Max Activating Token Index: 348

Text #19

Max Range: 4.7491. Min Range: -4.7491

Max Act: 4.4883. Min Act: -0.1700

Data Index: 579314 (Open Web Text)

Max Activating Token Index: 559