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

Dataset: Open Web Text

Neuron 763 in Layer 3

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: 3.9406. Min Range: -3.9406

Max Act: 3.9406. Min Act: -0.1700

Data Index: 742719 (Open Web Text)

Max Activating Token Index: 946

Text #1

Max Range: 3.9406. Min Range: -3.9406

Max Act: 3.8539. Min Act: -0.1700

Data Index: 3016875 (Open Web Text)

Max Activating Token Index: 682

Text #2

Max Range: 3.9406. Min Range: -3.9406

Max Act: 3.8425. Min Act: -0.1700

Data Index: 5505611 (Open Web Text)

Max Activating Token Index: 678

Text #3

Max Range: 3.9406. Min Range: -3.9406

Max Act: 3.7874. Min Act: -0.1700

Data Index: 542816 (Open Web Text)

Max Activating Token Index: 593

Text #4

Max Range: 3.9406. Min Range: -3.9406

Max Act: 3.8389. Min Act: -0.1700

Data Index: 4131764 (Open Web Text)

Max Activating Token Index: 452

Text #5

Max Range: 3.9406. Min Range: -3.9406

Max Act: 3.7760. Min Act: -0.1700

Data Index: 3115846 (Open Web Text)

Max Activating Token Index: 522

Text #6

Max Range: 3.9406. Min Range: -3.9406

Max Act: 3.7495. Min Act: -0.1700

Data Index: 352397 (Open Web Text)

Max Activating Token Index: 680

Text #7

Max Range: 3.9406. Min Range: -3.9406

Max Act: 3.7596. Min Act: -0.1700

Data Index: 8581561 (Open Web Text)

Max Activating Token Index: 467

Text #8

Max Range: 3.9406. Min Range: -3.9406

Max Act: 3.7514. Min Act: -0.1700

Data Index: 4153505 (Open Web Text)

Max Activating Token Index: 652

Text #9

Max Range: 3.9406. Min Range: -3.9406

Max Act: 3.7141. Min Act: -0.1700

Data Index: 6021051 (Open Web Text)

Max Activating Token Index: 264

Text #10

Max Range: 3.9406. Min Range: -3.9406

Max Act: 3.6807. Min Act: -0.1700

Data Index: 5615034 (Open Web Text)

Max Activating Token Index: 673

Text #11

Max Range: 3.9406. Min Range: -3.9406

Max Act: 3.7424. Min Act: -0.1700

Data Index: 3009186 (Open Web Text)

Max Activating Token Index: 240

Text #12

Max Range: 3.9406. Min Range: -3.9406

Max Act: 3.7025. Min Act: -0.1700

Data Index: 302562 (Open Web Text)

Max Activating Token Index: 494

Text #13

Max Range: 3.9406. Min Range: -3.9406

Max Act: 3.7344. Min Act: -0.1700

Data Index: 2502454 (Open Web Text)

Max Activating Token Index: 862

Text #14

Max Range: 3.9406. Min Range: -3.9406

Max Act: 3.7011. Min Act: -0.1700

Data Index: 2486016 (Open Web Text)

Max Activating Token Index: 503

Text #15

Max Range: 3.9406. Min Range: -3.9406

Max Act: 3.6890. Min Act: -0.1700

Data Index: 3303932 (Open Web Text)

Max Activating Token Index: 938

Text #16

Max Range: 3.9406. Min Range: -3.9406

Max Act: 3.6992. Min Act: -0.1700

Data Index: 2760431 (Open Web Text)

Max Activating Token Index: 744

Text #17

Max Range: 3.9406. Min Range: -3.9406

Max Act: 3.6801. Min Act: -0.1700

Data Index: 7143786 (Open Web Text)

Max Activating Token Index: 705

Text #18

Max Range: 3.9406. Min Range: -3.9406

Max Act: 3.6714. Min Act: -0.1700

Data Index: 6159574 (Open Web Text)

Max Activating Token Index: 811

Text #19

Max Range: 3.9406. Min Range: -3.9406

Max Act: 3.6457. Min Act: -0.1700

Data Index: 2336334 (Open Web Text)

Max Activating Token Index: 1019