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

Dataset: Open Web Text

Neuron 1035 in Layer 3

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: 1.9820. Min Range: -1.9820

Max Act: 1.9820. Min Act: -0.1700

Data Index: 2479188 (Open Web Text)

Max Activating Token Index: 376

Text #1

Max Range: 1.9820. Min Range: -1.9820

Max Act: 1.9573. Min Act: -0.1700

Data Index: 1591872 (Open Web Text)

Max Activating Token Index: 915

Text #2

Max Range: 1.9820. Min Range: -1.9820

Max Act: 1.9518. Min Act: -0.1700

Data Index: 3266136 (Open Web Text)

Max Activating Token Index: 669

Text #3

Max Range: 1.9820. Min Range: -1.9820

Max Act: 1.9309. Min Act: -0.1700

Data Index: 7090463 (Open Web Text)

Max Activating Token Index: 392

Text #4

Max Range: 1.9820. Min Range: -1.9820

Max Act: 1.8993. Min Act: -0.1700

Data Index: 1812335 (Open Web Text)

Max Activating Token Index: 270

Text #5

Max Range: 1.9820. Min Range: -1.9820

Max Act: 1.8815. Min Act: -0.1700

Data Index: 7990366 (Open Web Text)

Max Activating Token Index: 382

Text #6

Max Range: 1.9820. Min Range: -1.9820

Max Act: 1.8858. Min Act: -0.1700

Data Index: 4209039 (Open Web Text)

Max Activating Token Index: 751

Text #7

Max Range: 1.9820. Min Range: -1.9820

Max Act: 1.8787. Min Act: -0.1700

Data Index: 2412635 (Open Web Text)

Max Activating Token Index: 411

Text #8

Max Range: 1.9820. Min Range: -1.9820

Max Act: 1.8527. Min Act: -0.1700

Data Index: 6708165 (Open Web Text)

Max Activating Token Index: 865

Text #9

Max Range: 1.9820. Min Range: -1.9820

Max Act: 1.8811. Min Act: -0.1700

Data Index: 2285401 (Open Web Text)

Max Activating Token Index: 670

Text #10

Max Range: 1.9820. Min Range: -1.9820

Max Act: 1.8779. Min Act: -0.1700

Data Index: 2958731 (Open Web Text)

Max Activating Token Index: 407

Text #11

Max Range: 1.9820. Min Range: -1.9820

Max Act: 1.8558. Min Act: -0.1700

Data Index: 2990667 (Open Web Text)

Max Activating Token Index: 538

Text #12

Max Range: 1.9820. Min Range: -1.9820

Max Act: 1.8480. Min Act: -0.1700

Data Index: 3147241 (Open Web Text)

Max Activating Token Index: 817

Text #13

Max Range: 1.9820. Min Range: -1.9820

Max Act: 1.8508. Min Act: -0.1700

Data Index: 7330472 (Open Web Text)

Max Activating Token Index: 597

Text #14

Max Range: 1.9820. Min Range: -1.9820

Max Act: 1.8476. Min Act: -0.1700

Data Index: 1866885 (Open Web Text)

Max Activating Token Index: 385

Text #15

Max Range: 1.9820. Min Range: -1.9820

Max Act: 1.8386. Min Act: -0.1700

Data Index: 2729684 (Open Web Text)

Max Activating Token Index: 40

Text #16

Max Range: 1.9820. Min Range: -1.9820

Max Act: 1.8377. Min Act: -0.1700

Data Index: 7507320 (Open Web Text)

Max Activating Token Index: 691

Text #17

Max Range: 1.9820. Min Range: -1.9820

Max Act: 1.8349. Min Act: -0.1700

Data Index: 5775067 (Open Web Text)

Max Activating Token Index: 146

Text #18

Max Range: 1.9820. Min Range: -1.9820

Max Act: 1.8385. Min Act: -0.1700

Data Index: 1084910 (Open Web Text)

Max Activating Token Index: 520

Text #19

Max Range: 1.9820. Min Range: -1.9820

Max Act: 1.8281. Min Act: -0.1700

Data Index: 3990664 (Open Web Text)

Max Activating Token Index: 476