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

Dataset: Open Web Text

Neuron 318 in Layer 6

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: 3.1451. Min Range: -3.1451

Max Act: 3.1345. Min Act: -0.1700

Data Index: 670660 (Open Web Text)

Max Activating Token Index: 936

Text #1

Max Range: 3.1451. Min Range: -3.1451

Max Act: 3.1371. Min Act: -0.1700

Data Index: 6849472 (Open Web Text)

Max Activating Token Index: 664

Text #2

Max Range: 3.1451. Min Range: -3.1451

Max Act: 3.1451. Min Act: -0.1700

Data Index: 3669234 (Open Web Text)

Max Activating Token Index: 597

Text #3

Max Range: 3.1451. Min Range: -3.1451

Max Act: 3.1041. Min Act: -0.1700

Data Index: 2714020 (Open Web Text)

Max Activating Token Index: 201

Text #4

Max Range: 3.1451. Min Range: -3.1451

Max Act: 3.1044. Min Act: -0.1700

Data Index: 8646418 (Open Web Text)

Max Activating Token Index: 295

Text #5

Max Range: 3.1451. Min Range: -3.1451

Max Act: 3.0795. Min Act: -0.1700

Data Index: 6206810 (Open Web Text)

Max Activating Token Index: 897

Text #6

Max Range: 3.1451. Min Range: -3.1451

Max Act: 3.0541. Min Act: -0.1700

Data Index: 7125543 (Open Web Text)

Max Activating Token Index: 488

Text #7

Max Range: 3.1451. Min Range: -3.1451

Max Act: 3.0196. Min Act: -0.1700

Data Index: 546146 (Open Web Text)

Max Activating Token Index: 571

Text #8

Max Range: 3.1451. Min Range: -3.1451

Max Act: 3.0382. Min Act: -0.1700

Data Index: 5616700 (Open Web Text)

Max Activating Token Index: 553

Text #9

Max Range: 3.1451. Min Range: -3.1451

Max Act: 2.9938. Min Act: -0.1700

Data Index: 3640082 (Open Web Text)

Max Activating Token Index: 558

Text #10

Max Range: 3.1451. Min Range: -3.1451

Max Act: 2.9794. Min Act: -0.1700

Data Index: 3676650 (Open Web Text)

Max Activating Token Index: 349

Text #11

Max Range: 3.1451. Min Range: -3.1451

Max Act: 3.0020. Min Act: -0.1700

Data Index: 1105437 (Open Web Text)

Max Activating Token Index: 237

Text #12

Max Range: 3.1451. Min Range: -3.1451

Max Act: 2.9829. Min Act: -0.1700

Data Index: 5719016 (Open Web Text)

Max Activating Token Index: 306

Text #13

Max Range: 3.1451. Min Range: -3.1451

Max Act: 2.9763. Min Act: -0.1700

Data Index: 3193731 (Open Web Text)

Max Activating Token Index: 911

Text #14

Max Range: 3.1451. Min Range: -3.1451

Max Act: 2.9801. Min Act: -0.1700

Data Index: 5311084 (Open Web Text)

Max Activating Token Index: 381

Text #15

Max Range: 3.1451. Min Range: -3.1451

Max Act: 2.9827. Min Act: -0.1700

Data Index: 2486027 (Open Web Text)

Max Activating Token Index: 161

Text #16

Max Range: 3.1451. Min Range: -3.1451

Max Act: 2.9514. Min Act: -0.1700

Data Index: 3950694 (Open Web Text)

Max Activating Token Index: 524

Text #17

Max Range: 3.1451. Min Range: -3.1451

Max Act: 2.9611. Min Act: -0.1700

Data Index: 757120 (Open Web Text)

Max Activating Token Index: 349

Text #18

Max Range: 3.1451. Min Range: -3.1451

Max Act: 2.9557. Min Act: -0.1700

Data Index: 5544836 (Open Web Text)

Max Activating Token Index: 683

Text #19

Max Range: 3.1451. Min Range: -3.1451

Max Act: 2.9543. Min Act: -0.1700

Data Index: 6800028 (Open Web Text)

Max Activating Token Index: 698