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

Dataset: Open Web Text

Neuron 1181 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: 1.7650. Min Range: -1.7650

Max Act: 1.7531. Min Act: -0.1700

Data Index: 8390737 (Open Web Text)

Max Activating Token Index: 372

Text #1

Max Range: 1.7650. Min Range: -1.7650

Max Act: 1.7545. Min Act: -0.1700

Data Index: 7407532 (Open Web Text)

Max Activating Token Index: 293

Text #2

Max Range: 1.7650. Min Range: -1.7650

Max Act: 1.7650. Min Act: -0.1700

Data Index: 8089491 (Open Web Text)

Max Activating Token Index: 517

Text #3

Max Range: 1.7650. Min Range: -1.7650

Max Act: 1.7495. Min Act: -0.1700

Data Index: 1613288 (Open Web Text)

Max Activating Token Index: 115

Text #4

Max Range: 1.7650. Min Range: -1.7650

Max Act: 1.7479. Min Act: -0.1700

Data Index: 7993328 (Open Web Text)

Max Activating Token Index: 254

Text #5

Max Range: 1.7650. Min Range: -1.7650

Max Act: 1.7306. Min Act: -0.1700

Data Index: 8349903 (Open Web Text)

Max Activating Token Index: 969

Text #6

Max Range: 1.7650. Min Range: -1.7650

Max Act: 1.7293. Min Act: -0.1700

Data Index: 1832971 (Open Web Text)

Max Activating Token Index: 408

Text #7

Max Range: 1.7650. Min Range: -1.7650

Max Act: 1.7047. Min Act: -0.1700

Data Index: 2105020 (Open Web Text)

Max Activating Token Index: 424

Text #8

Max Range: 1.7650. Min Range: -1.7650

Max Act: 1.7158. Min Act: -0.1700

Data Index: 5027527 (Open Web Text)

Max Activating Token Index: 951

Text #9

Max Range: 1.7650. Min Range: -1.7650

Max Act: 1.6986. Min Act: -0.1700

Data Index: 5317791 (Open Web Text)

Max Activating Token Index: 170

Text #10

Max Range: 1.7650. Min Range: -1.7650

Max Act: 1.6846. Min Act: -0.1700

Data Index: 2988430 (Open Web Text)

Max Activating Token Index: 473

Text #11

Max Range: 1.7650. Min Range: -1.7650

Max Act: 1.6813. Min Act: -0.1700

Data Index: 235436 (Open Web Text)

Max Activating Token Index: 259

Text #12

Max Range: 1.7650. Min Range: -1.7650

Max Act: 1.6795. Min Act: -0.1700

Data Index: 2058853 (Open Web Text)

Max Activating Token Index: 777

Text #13

Max Range: 1.7650. Min Range: -1.7650

Max Act: 1.6835. Min Act: -0.1700

Data Index: 2634805 (Open Web Text)

Max Activating Token Index: 105

Text #14

Max Range: 1.7650. Min Range: -1.7650

Max Act: 1.6820. Min Act: -0.1700

Data Index: 8606879 (Open Web Text)

Max Activating Token Index: 388

Text #15

Max Range: 1.7650. Min Range: -1.7650

Max Act: 1.6658. Min Act: -0.1700

Data Index: 2969728 (Open Web Text)

Max Activating Token Index: 541

Text #16

Max Range: 1.7650. Min Range: -1.7650

Max Act: 1.6731. Min Act: -0.1700

Data Index: 5506672 (Open Web Text)

Max Activating Token Index: 905

Text #17

Max Range: 1.7650. Min Range: -1.7650

Max Act: 1.6690. Min Act: -0.1700

Data Index: 5810276 (Open Web Text)

Max Activating Token Index: 321

Text #18

Max Range: 1.7650. Min Range: -1.7650

Max Act: 1.6757. Min Act: -0.1700

Data Index: 1672908 (Open Web Text)

Max Activating Token Index: 103

Text #19

Max Range: 1.7650. Min Range: -1.7650

Max Act: 1.6717. Min Act: -0.1700

Data Index: 519144 (Open Web Text)

Max Activating Token Index: 290