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

Dataset: Open Web Text

Neuron 1507 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: 4.0038. Min Range: -4.0038

Max Act: 4.0038. Min Act: -0.1700

Data Index: 4429943 (Open Web Text)

Max Activating Token Index: 940

Text #1

Max Range: 4.0038. Min Range: -4.0038

Max Act: 3.9794. Min Act: -0.1700

Data Index: 8393850 (Open Web Text)

Max Activating Token Index: 602

Text #2

Max Range: 4.0038. Min Range: -4.0038

Max Act: 3.9637. Min Act: -0.1700

Data Index: 7665390 (Open Web Text)

Max Activating Token Index: 512

Text #3

Max Range: 4.0038. Min Range: -4.0038

Max Act: 3.9433. Min Act: -0.1700

Data Index: 7094110 (Open Web Text)

Max Activating Token Index: 742

Text #4

Max Range: 4.0038. Min Range: -4.0038

Max Act: 3.9302. Min Act: -0.1700

Data Index: 6991959 (Open Web Text)

Max Activating Token Index: 296

Text #5

Max Range: 4.0038. Min Range: -4.0038

Max Act: 3.9497. Min Act: -0.1700

Data Index: 6761899 (Open Web Text)

Max Activating Token Index: 478

Text #6

Max Range: 4.0038. Min Range: -4.0038

Max Act: 3.9436. Min Act: -0.1700

Data Index: 7156680 (Open Web Text)

Max Activating Token Index: 807

Text #7

Max Range: 4.0038. Min Range: -4.0038

Max Act: 3.9376. Min Act: -0.1700

Data Index: 5810344 (Open Web Text)

Max Activating Token Index: 299

Text #8

Max Range: 4.0038. Min Range: -4.0038

Max Act: 3.9684. Min Act: -0.1700

Data Index: 1635292 (Open Web Text)

Max Activating Token Index: 685

Text #9

Max Range: 4.0038. Min Range: -4.0038

Max Act: 3.9301. Min Act: -0.1700

Data Index: 4473299 (Open Web Text)

Max Activating Token Index: 919

Text #10

Max Range: 4.0038. Min Range: -4.0038

Max Act: 3.9021. Min Act: -0.1700

Data Index: 3575919 (Open Web Text)

Max Activating Token Index: 680

Text #11

Max Range: 4.0038. Min Range: -4.0038

Max Act: 3.9111. Min Act: -0.1700

Data Index: 5103231 (Open Web Text)

Max Activating Token Index: 389

Text #12

Max Range: 4.0038. Min Range: -4.0038

Max Act: 3.9162. Min Act: -0.1700

Data Index: 856519 (Open Web Text)

Max Activating Token Index: 497

Text #13

Max Range: 4.0038. Min Range: -4.0038

Max Act: 3.9092. Min Act: -0.1700

Data Index: 2744339 (Open Web Text)

Max Activating Token Index: 802

Text #14

Max Range: 4.0038. Min Range: -4.0038

Max Act: 3.9139. Min Act: -0.1700

Data Index: 6892919 (Open Web Text)

Max Activating Token Index: 506

Text #15

Max Range: 4.0038. Min Range: -4.0038

Max Act: 3.9277. Min Act: -0.1700

Data Index: 1978098 (Open Web Text)

Max Activating Token Index: 944

Text #16

Max Range: 4.0038. Min Range: -4.0038

Max Act: 3.9168. Min Act: -0.1700

Data Index: 2257441 (Open Web Text)

Max Activating Token Index: 291

Text #17

Max Range: 4.0038. Min Range: -4.0038

Max Act: 3.9243. Min Act: -0.1700

Data Index: 752910 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 4.0038. Min Range: -4.0038

Max Act: 3.9269. Min Act: -0.1700

Data Index: 1565254 (Open Web Text)

Max Activating Token Index: 830

Text #19

Max Range: 4.0038. Min Range: -4.0038

Max Act: 3.9190. Min Act: -0.1700

Data Index: 7964910 (Open Web Text)

Max Activating Token Index: 288