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

Dataset: Open Web Text

Neuron 732 in Layer 2

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: 1.6457. Min Range: -1.6457

Max Act: 1.6457. Min Act: -0.1493

Data Index: 6919853 (Open Web Text)

Max Activating Token Index: 790

Text #1

Max Range: 1.6457. Min Range: -1.6457

Max Act: 1.6235. Min Act: -0.1690

Data Index: 5023519 (Open Web Text)

Max Activating Token Index: 825

Text #2

Max Range: 1.6457. Min Range: -1.6457

Max Act: 1.6056. Min Act: -0.1654

Data Index: 5646678 (Open Web Text)

Max Activating Token Index: 126

Text #3

Max Range: 1.6457. Min Range: -1.6457

Max Act: 1.5861. Min Act: -0.1616

Data Index: 4031566 (Open Web Text)

Max Activating Token Index: 447

Text #4

Max Range: 1.6457. Min Range: -1.6457

Max Act: 1.6078. Min Act: -0.1692

Data Index: 5697775 (Open Web Text)

Max Activating Token Index: 547

Text #5

Max Range: 1.6457. Min Range: -1.6457

Max Act: 1.5908. Min Act: -0.1700

Data Index: 7972901 (Open Web Text)

Max Activating Token Index: 459

Text #6

Max Range: 1.6457. Min Range: -1.6457

Max Act: 1.5846. Min Act: -0.1690

Data Index: 5697772 (Open Web Text)

Max Activating Token Index: 580

Text #7

Max Range: 1.6457. Min Range: -1.6457

Max Act: 1.5807. Min Act: -0.1700

Data Index: 7170836 (Open Web Text)

Max Activating Token Index: 223

Text #8

Max Range: 1.6457. Min Range: -1.6457

Max Act: 1.5990. Min Act: -0.1569

Data Index: 7577357 (Open Web Text)

Max Activating Token Index: 656

Text #9

Max Range: 1.6457. Min Range: -1.6457

Max Act: 1.5795. Min Act: -0.1686

Data Index: 2177770 (Open Web Text)

Max Activating Token Index: 996

Text #10

Max Range: 1.6457. Min Range: -1.6457

Max Act: 1.5584. Min Act: -0.1695

Data Index: 8650666 (Open Web Text)

Max Activating Token Index: 510

Text #11

Max Range: 1.6457. Min Range: -1.6457

Max Act: 1.5719. Min Act: -0.1700

Data Index: 6804260 (Open Web Text)

Max Activating Token Index: 442

Text #12

Max Range: 1.6457. Min Range: -1.6457

Max Act: 1.5752. Min Act: -0.1625

Data Index: 920111 (Open Web Text)

Max Activating Token Index: 531

Text #13

Max Range: 1.6457. Min Range: -1.6457

Max Act: 1.5573. Min Act: -0.1699

Data Index: 7127925 (Open Web Text)

Max Activating Token Index: 450

Text #14

Max Range: 1.6457. Min Range: -1.6457

Max Act: 1.5694. Min Act: -0.1700

Data Index: 4408523 (Open Web Text)

Max Activating Token Index: 564

Text #15

Max Range: 1.6457. Min Range: -1.6457

Max Act: 1.5608. Min Act: -0.1685

Data Index: 3016630 (Open Web Text)

Max Activating Token Index: 186

Text #16

Max Range: 1.6457. Min Range: -1.6457

Max Act: 1.5574. Min Act: -0.1696

Data Index: 7625970 (Open Web Text)

Max Activating Token Index: 434

Text #17

Max Range: 1.6457. Min Range: -1.6457

Max Act: 1.5677. Min Act: -0.1698

Data Index: 5405881 (Open Web Text)

Max Activating Token Index: 390

Text #18

Max Range: 1.6457. Min Range: -1.6457

Max Act: 1.5441. Min Act: -0.1695

Data Index: 5576439 (Open Web Text)

Max Activating Token Index: 625

Text #19

Max Range: 1.6457. Min Range: -1.6457

Max Act: 1.5614. Min Act: -0.1656

Data Index: 4941966 (Open Web Text)

Max Activating Token Index: 133