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

Dataset: Open Web Text

Neuron 329 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: 4.1069. Min Range: -4.1069

Max Act: 4.1069. Min Act: -0.1700

Data Index: 3537427 (Open Web Text)

Max Activating Token Index: 52

Text #1

Max Range: 4.1069. Min Range: -4.1069

Max Act: 4.0744. Min Act: -0.1700

Data Index: 5427312 (Open Web Text)

Max Activating Token Index: 331

Text #2

Max Range: 4.1069. Min Range: -4.1069

Max Act: 4.0625. Min Act: -0.1700

Data Index: 4653130 (Open Web Text)

Max Activating Token Index: 496

Text #3

Max Range: 4.1069. Min Range: -4.1069

Max Act: 4.0434. Min Act: -0.1700

Data Index: 3427493 (Open Web Text)

Max Activating Token Index: 395

Text #4

Max Range: 4.1069. Min Range: -4.1069

Max Act: 4.0468. Min Act: -0.1700

Data Index: 6057910 (Open Web Text)

Max Activating Token Index: 314

Text #5

Max Range: 4.1069. Min Range: -4.1069

Max Act: 4.0378. Min Act: -0.1700

Data Index: 295112 (Open Web Text)

Max Activating Token Index: 458

Text #6

Max Range: 4.1069. Min Range: -4.1069

Max Act: 3.9936. Min Act: -0.1700

Data Index: 1009932 (Open Web Text)

Max Activating Token Index: 578

Text #7

Max Range: 4.1069. Min Range: -4.1069

Max Act: 3.9816. Min Act: -0.1700

Data Index: 7625205 (Open Web Text)

Max Activating Token Index: 454

Text #8

Max Range: 4.1069. Min Range: -4.1069

Max Act: 3.9877. Min Act: -0.1700

Data Index: 6400866 (Open Web Text)

Max Activating Token Index: 633

Text #9

Max Range: 4.1069. Min Range: -4.1069

Max Act: 3.9506. Min Act: -0.1700

Data Index: 438003 (Open Web Text)

Max Activating Token Index: 179

Text #10

Max Range: 4.1069. Min Range: -4.1069

Max Act: 3.9779. Min Act: -0.1700

Data Index: 6149890 (Open Web Text)

Max Activating Token Index: 475

Text #11

Max Range: 4.1069. Min Range: -4.1069

Max Act: 3.9738. Min Act: -0.1700

Data Index: 2121287 (Open Web Text)

Max Activating Token Index: 835

Text #12

Max Range: 4.1069. Min Range: -4.1069

Max Act: 3.9765. Min Act: -0.1700

Data Index: 613324 (Open Web Text)

Max Activating Token Index: 244

Text #13

Max Range: 4.1069. Min Range: -4.1069

Max Act: 3.9814. Min Act: -0.1700

Data Index: 938394 (Open Web Text)

Max Activating Token Index: 16

Text #14

Max Range: 4.1069. Min Range: -4.1069

Max Act: 3.9669. Min Act: -0.1700

Data Index: 6116775 (Open Web Text)

Max Activating Token Index: 712

Text #15

Max Range: 4.1069. Min Range: -4.1069

Max Act: 3.9495. Min Act: -0.1700

Data Index: 3080702 (Open Web Text)

Max Activating Token Index: 367

Text #16

Max Range: 4.1069. Min Range: -4.1069

Max Act: 3.9343. Min Act: -0.1700

Data Index: 8565810 (Open Web Text)

Max Activating Token Index: 506

Text #17

Max Range: 4.1069. Min Range: -4.1069

Max Act: 3.9380. Min Act: -0.1700

Data Index: 6718262 (Open Web Text)

Max Activating Token Index: 179

Text #18

Max Range: 4.1069. Min Range: -4.1069

Max Act: 3.8974. Min Act: -0.1700

Data Index: 2293815 (Open Web Text)

Max Activating Token Index: 687

Text #19

Max Range: 4.1069. Min Range: -4.1069

Max Act: 3.9196. Min Act: -0.1700

Data Index: 3524565 (Open Web Text)

Max Activating Token Index: 955