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

Dataset: Open Web Text

Neuron 2640 in Layer 0

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: 4.0857. Min Range: -4.0857

Max Act: 4.0857. Min Act: -0.1700

Data Index: 1979220 (Open Web Text)

Max Activating Token Index: 745

Text #1

Max Range: 4.0857. Min Range: -4.0857

Max Act: 4.0197. Min Act: -0.1700

Data Index: 1792776 (Open Web Text)

Max Activating Token Index: 350

Text #2

Max Range: 4.0857. Min Range: -4.0857

Max Act: 3.8528. Min Act: -0.1700

Data Index: 7931624 (Open Web Text)

Max Activating Token Index: 50

Text #3

Max Range: 4.0857. Min Range: -4.0857

Max Act: 3.8229. Min Act: -0.1700

Data Index: 3626459 (Open Web Text)

Max Activating Token Index: 346

Text #4

Max Range: 4.0857. Min Range: -4.0857

Max Act: 3.8147. Min Act: -0.1700

Data Index: 7424894 (Open Web Text)

Max Activating Token Index: 954

Text #5

Max Range: 4.0857. Min Range: -4.0857

Max Act: 3.7540. Min Act: -0.1700

Data Index: 2801536 (Open Web Text)

Max Activating Token Index: 439

Text #6

Max Range: 4.0857. Min Range: -4.0857

Max Act: 3.7652. Min Act: -0.1700

Data Index: 6219231 (Open Web Text)

Max Activating Token Index: 548

Text #7

Max Range: 4.0857. Min Range: -4.0857

Max Act: 3.7889. Min Act: -0.1700

Data Index: 7750645 (Open Web Text)

Max Activating Token Index: 340

Text #8

Max Range: 4.0857. Min Range: -4.0857

Max Act: 3.7708. Min Act: -0.1700

Data Index: 4426006 (Open Web Text)

Max Activating Token Index: 696

Text #9

Max Range: 4.0857. Min Range: -4.0857

Max Act: 3.7307. Min Act: -0.1700

Data Index: 5209679 (Open Web Text)

Max Activating Token Index: 141

Text #10

Max Range: 4.0857. Min Range: -4.0857

Max Act: 3.7438. Min Act: -0.1700

Data Index: 2754789 (Open Web Text)

Max Activating Token Index: 743

Text #11

Max Range: 4.0857. Min Range: -4.0857

Max Act: 3.7575. Min Act: -0.1700

Data Index: 7014421 (Open Web Text)

Max Activating Token Index: 722

Text #12

Max Range: 4.0857. Min Range: -4.0857

Max Act: 3.7247. Min Act: -0.1700

Data Index: 2984514 (Open Web Text)

Max Activating Token Index: 603

Text #13

Max Range: 4.0857. Min Range: -4.0857

Max Act: 3.7333. Min Act: -0.1700

Data Index: 6789722 (Open Web Text)

Max Activating Token Index: 731

Text #14

Max Range: 4.0857. Min Range: -4.0857

Max Act: 3.7339. Min Act: -0.1700

Data Index: 4167326 (Open Web Text)

Max Activating Token Index: 260

Text #15

Max Range: 4.0857. Min Range: -4.0857

Max Act: 3.6894. Min Act: -0.1700

Data Index: 7096716 (Open Web Text)

Max Activating Token Index: 785

Text #16

Max Range: 4.0857. Min Range: -4.0857

Max Act: 3.7124. Min Act: -0.1700

Data Index: 7381786 (Open Web Text)

Max Activating Token Index: 224

Text #17

Max Range: 4.0857. Min Range: -4.0857

Max Act: 3.7029. Min Act: -0.1700

Data Index: 3149063 (Open Web Text)

Max Activating Token Index: 268

Text #18

Max Range: 4.0857. Min Range: -4.0857

Max Act: 3.7276. Min Act: -0.1700

Data Index: 2698463 (Open Web Text)

Max Activating Token Index: 718

Text #19

Max Range: 4.0857. Min Range: -4.0857

Max Act: 3.6909. Min Act: -0.1700

Data Index: 5206758 (Open Web Text)

Max Activating Token Index: 891