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

Dataset: Open Web Text

Neuron 2541 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: 0.9534. Min Range: -0.9534

Max Act: 0.9534. Min Act: -0.1700

Data Index: 2641867 (Open Web Text)

Max Activating Token Index: 575

Text #1

Max Range: 0.9534. Min Range: -0.9534

Max Act: 0.9521. Min Act: -0.1700

Data Index: 2562559 (Open Web Text)

Max Activating Token Index: 584

Text #2

Max Range: 0.9534. Min Range: -0.9534

Max Act: 0.9490. Min Act: -0.1700

Data Index: 3132307 (Open Web Text)

Max Activating Token Index: 583

Text #3

Max Range: 0.9534. Min Range: -0.9534

Max Act: 0.9404. Min Act: -0.1700

Data Index: 5684144 (Open Web Text)

Max Activating Token Index: 594

Text #4

Max Range: 0.9534. Min Range: -0.9534

Max Act: 0.9410. Min Act: -0.1700

Data Index: 8371771 (Open Web Text)

Max Activating Token Index: 594

Text #5

Max Range: 0.9534. Min Range: -0.9534

Max Act: 0.9421. Min Act: -0.1700

Data Index: 6066989 (Open Web Text)

Max Activating Token Index: 611

Text #6

Max Range: 0.9534. Min Range: -0.9534

Max Act: 0.9410. Min Act: -0.1700

Data Index: 2271205 (Open Web Text)

Max Activating Token Index: 578

Text #7

Max Range: 0.9534. Min Range: -0.9534

Max Act: 0.9445. Min Act: -0.1700

Data Index: 2238616 (Open Web Text)

Max Activating Token Index: 596

Text #8

Max Range: 0.9534. Min Range: -0.9534

Max Act: 0.9310. Min Act: -0.1700

Data Index: 7450153 (Open Web Text)

Max Activating Token Index: 602

Text #9

Max Range: 0.9534. Min Range: -0.9534

Max Act: 0.9277. Min Act: -0.1700

Data Index: 91700 (Open Web Text)

Max Activating Token Index: 606

Text #10

Max Range: 0.9534. Min Range: -0.9534

Max Act: 0.9291. Min Act: -0.1700

Data Index: 2486629 (Open Web Text)

Max Activating Token Index: 622

Text #11

Max Range: 0.9534. Min Range: -0.9534

Max Act: 0.9331. Min Act: -0.1700

Data Index: 3787283 (Open Web Text)

Max Activating Token Index: 591

Text #12

Max Range: 0.9534. Min Range: -0.9534

Max Act: 0.9359. Min Act: -0.1700

Data Index: 1750121 (Open Web Text)

Max Activating Token Index: 603

Text #13

Max Range: 0.9534. Min Range: -0.9534

Max Act: 0.9288. Min Act: -0.1700

Data Index: 6439502 (Open Web Text)

Max Activating Token Index: 595

Text #14

Max Range: 0.9534. Min Range: -0.9534

Max Act: 0.9263. Min Act: -0.1700

Data Index: 743517 (Open Web Text)

Max Activating Token Index: 612

Text #15

Max Range: 0.9534. Min Range: -0.9534

Max Act: 0.9309. Min Act: -0.1700

Data Index: 3225018 (Open Web Text)

Max Activating Token Index: 601

Text #16

Max Range: 0.9534. Min Range: -0.9534

Max Act: 0.9215. Min Act: -0.1700

Data Index: 2674326 (Open Web Text)

Max Activating Token Index: 601

Text #17

Max Range: 0.9534. Min Range: -0.9534

Max Act: 0.9365. Min Act: -0.1700

Data Index: 2180695 (Open Web Text)

Max Activating Token Index: 588

Text #18

Max Range: 0.9534. Min Range: -0.9534

Max Act: 0.9188. Min Act: -0.1700

Data Index: 310491 (Open Web Text)

Max Activating Token Index: 606

Text #19

Max Range: 0.9534. Min Range: -0.9534

Max Act: 0.9242. Min Act: -0.1700

Data Index: 4265882 (Open Web Text)

Max Activating Token Index: 606