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

Dataset: Open Web Text

Neuron 2290 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: 3.9281. Min Range: -3.9281

Max Act: 3.9281. Min Act: -0.1700

Data Index: 2427128 (Open Web Text)

Max Activating Token Index: 675

Text #1

Max Range: 3.9281. Min Range: -3.9281

Max Act: 3.7812. Min Act: -0.1700

Data Index: 1761838 (Open Web Text)

Max Activating Token Index: 683

Text #2

Max Range: 3.9281. Min Range: -3.9281

Max Act: 3.7568. Min Act: -0.1700

Data Index: 6631987 (Open Web Text)

Max Activating Token Index: 132

Text #3

Max Range: 3.9281. Min Range: -3.9281

Max Act: 3.8010. Min Act: -0.1700

Data Index: 3704584 (Open Web Text)

Max Activating Token Index: 452

Text #4

Max Range: 3.9281. Min Range: -3.9281

Max Act: 3.7324. Min Act: -0.1700

Data Index: 4878436 (Open Web Text)

Max Activating Token Index: 198

Text #5

Max Range: 3.9281. Min Range: -3.9281

Max Act: 3.7496. Min Act: -0.1700

Data Index: 6980254 (Open Web Text)

Max Activating Token Index: 854

Text #6

Max Range: 3.9281. Min Range: -3.9281

Max Act: 3.7555. Min Act: -0.1700

Data Index: 386408 (Open Web Text)

Max Activating Token Index: 473

Text #7

Max Range: 3.9281. Min Range: -3.9281

Max Act: 3.7370. Min Act: -0.1700

Data Index: 4179025 (Open Web Text)

Max Activating Token Index: 254

Text #8

Max Range: 3.9281. Min Range: -3.9281

Max Act: 3.7199. Min Act: -0.1700

Data Index: 6745333 (Open Web Text)

Max Activating Token Index: 679

Text #9

Max Range: 3.9281. Min Range: -3.9281

Max Act: 3.7007. Min Act: -0.1700

Data Index: 4755787 (Open Web Text)

Max Activating Token Index: 430

Text #10

Max Range: 3.9281. Min Range: -3.9281

Max Act: 3.6982. Min Act: -0.1700

Data Index: 8832557 (Open Web Text)

Max Activating Token Index: 31

Text #11

Max Range: 3.9281. Min Range: -3.9281

Max Act: 3.6682. Min Act: -0.1700

Data Index: 7018317 (Open Web Text)

Max Activating Token Index: 903

Text #12

Max Range: 3.9281. Min Range: -3.9281

Max Act: 3.6645. Min Act: -0.1700

Data Index: 2931319 (Open Web Text)

Max Activating Token Index: 941

Text #13

Max Range: 3.9281. Min Range: -3.9281

Max Act: 3.6953. Min Act: -0.1700

Data Index: 8411939 (Open Web Text)

Max Activating Token Index: 1020

Text #14

Max Range: 3.9281. Min Range: -3.9281

Max Act: 3.6721. Min Act: -0.1700

Data Index: 8239259 (Open Web Text)

Max Activating Token Index: 356

Text #15

Max Range: 3.9281. Min Range: -3.9281

Max Act: 3.6814. Min Act: -0.1700

Data Index: 3340679 (Open Web Text)

Max Activating Token Index: 37

Text #16

Max Range: 3.9281. Min Range: -3.9281

Max Act: 3.6903. Min Act: -0.1700

Data Index: 1987407 (Open Web Text)

Max Activating Token Index: 981

Text #17

Max Range: 3.9281. Min Range: -3.9281

Max Act: 3.6813. Min Act: -0.1700

Data Index: 5979934 (Open Web Text)

Max Activating Token Index: 527

Text #18

Max Range: 3.9281. Min Range: -3.9281

Max Act: 3.6836. Min Act: -0.1700

Data Index: 5797906 (Open Web Text)

Max Activating Token Index: 618

Text #19

Max Range: 3.9281. Min Range: -3.9281

Max Act: 3.6620. Min Act: -0.1700

Data Index: 5632112 (Open Web Text)

Max Activating Token Index: 481