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

Dataset: Open Web Text

Neuron 2970 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: 3.9321. Min Range: -3.9321

Max Act: 3.9321. Min Act: -0.1700

Data Index: 1056860 (Open Web Text)

Max Activating Token Index: 227

Text #1

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.6665. Min Act: -0.1700

Data Index: 8350369 (Open Web Text)

Max Activating Token Index: 392

Text #2

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.7064. Min Act: -0.1700

Data Index: 4994328 (Open Web Text)

Max Activating Token Index: 763

Text #3

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.6975. Min Act: -0.1700

Data Index: 4506257 (Open Web Text)

Max Activating Token Index: 899

Text #4

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.6528. Min Act: -0.1700

Data Index: 6260635 (Open Web Text)

Max Activating Token Index: 350

Text #5

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.6520. Min Act: -0.1700

Data Index: 583548 (Open Web Text)

Max Activating Token Index: 838

Text #6

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.6444. Min Act: -0.1700

Data Index: 4019810 (Open Web Text)

Max Activating Token Index: 89

Text #7

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.5944. Min Act: -0.1700

Data Index: 5930364 (Open Web Text)

Max Activating Token Index: 507

Text #8

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.5691. Min Act: -0.1700

Data Index: 8447090 (Open Web Text)

Max Activating Token Index: 238

Text #9

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.5885. Min Act: -0.1700

Data Index: 451186 (Open Web Text)

Max Activating Token Index: 981

Text #10

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.5753. Min Act: -0.1700

Data Index: 8158247 (Open Web Text)

Max Activating Token Index: 891

Text #11

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.5680. Min Act: -0.1700

Data Index: 3196015 (Open Web Text)

Max Activating Token Index: 701

Text #12

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.5572. Min Act: -0.1700

Data Index: 5861642 (Open Web Text)

Max Activating Token Index: 356

Text #13

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.5589. Min Act: -0.1700

Data Index: 6174809 (Open Web Text)

Max Activating Token Index: 403

Text #14

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.5674. Min Act: -0.1700

Data Index: 6452038 (Open Web Text)

Max Activating Token Index: 614

Text #15

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.5421. Min Act: -0.1700

Data Index: 7038639 (Open Web Text)

Max Activating Token Index: 431

Text #16

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.5427. Min Act: -0.1700

Data Index: 6961599 (Open Web Text)

Max Activating Token Index: 986

Text #17

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.5242. Min Act: -0.1700

Data Index: 98280 (Open Web Text)

Max Activating Token Index: 937

Text #18

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.4753. Min Act: -0.1700

Data Index: 2886337 (Open Web Text)

Max Activating Token Index: 751

Text #19

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.4586. Min Act: -0.1700

Data Index: 3737443 (Open Web Text)

Max Activating Token Index: 201