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

Dataset: Open Web Text

Neuron 1565 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: 3.1295. Min Range: -3.1295

Max Act: 3.1295. Min Act: -0.1700

Data Index: 2512308 (Open Web Text)

Max Activating Token Index: 679

Text #1

Max Range: 3.1295. Min Range: -3.1295

Max Act: 3.0740. Min Act: -0.1700

Data Index: 7063704 (Open Web Text)

Max Activating Token Index: 954

Text #2

Max Range: 3.1295. Min Range: -3.1295

Max Act: 3.0534. Min Act: -0.1700

Data Index: 5211214 (Open Web Text)

Max Activating Token Index: 545

Text #3

Max Range: 3.1295. Min Range: -3.1295

Max Act: 3.0238. Min Act: -0.1700

Data Index: 726798 (Open Web Text)

Max Activating Token Index: 206

Text #4

Max Range: 3.1295. Min Range: -3.1295

Max Act: 3.0178. Min Act: -0.1700

Data Index: 899492 (Open Web Text)

Max Activating Token Index: 943

Text #5

Max Range: 3.1295. Min Range: -3.1295

Max Act: 2.9910. Min Act: -0.1700

Data Index: 1906525 (Open Web Text)

Max Activating Token Index: 484

Text #6

Max Range: 3.1295. Min Range: -3.1295

Max Act: 3.0432. Min Act: -0.1700

Data Index: 2253179 (Open Web Text)

Max Activating Token Index: 777

Text #7

Max Range: 3.1295. Min Range: -3.1295

Max Act: 3.0254. Min Act: -0.1700

Data Index: 2626565 (Open Web Text)

Max Activating Token Index: 658

Text #8

Max Range: 3.1295. Min Range: -3.1295

Max Act: 2.9965. Min Act: -0.1700

Data Index: 2415569 (Open Web Text)

Max Activating Token Index: 702

Text #9

Max Range: 3.1295. Min Range: -3.1295

Max Act: 3.0075. Min Act: -0.1700

Data Index: 939731 (Open Web Text)

Max Activating Token Index: 712

Text #10

Max Range: 3.1295. Min Range: -3.1295

Max Act: 3.0127. Min Act: -0.1700

Data Index: 1700386 (Open Web Text)

Max Activating Token Index: 702

Text #11

Max Range: 3.1295. Min Range: -3.1295

Max Act: 3.0153. Min Act: -0.1700

Data Index: 4050345 (Open Web Text)

Max Activating Token Index: 948

Text #12

Max Range: 3.1295. Min Range: -3.1295

Max Act: 3.0130. Min Act: -0.1700

Data Index: 2595314 (Open Web Text)

Max Activating Token Index: 38

Text #13

Max Range: 3.1295. Min Range: -3.1295

Max Act: 2.9847. Min Act: -0.1700

Data Index: 1339378 (Open Web Text)

Max Activating Token Index: 535

Text #14

Max Range: 3.1295. Min Range: -3.1295

Max Act: 2.9889. Min Act: -0.1700

Data Index: 413898 (Open Web Text)

Max Activating Token Index: 897

Text #15

Max Range: 3.1295. Min Range: -3.1295

Max Act: 3.0098. Min Act: -0.1700

Data Index: 8678977 (Open Web Text)

Max Activating Token Index: 897

Text #16

Max Range: 3.1295. Min Range: -3.1295

Max Act: 2.9872. Min Act: -0.1700

Data Index: 1388346 (Open Web Text)

Max Activating Token Index: 417

Text #17

Max Range: 3.1295. Min Range: -3.1295

Max Act: 2.9800. Min Act: -0.1700

Data Index: 3446736 (Open Web Text)

Max Activating Token Index: 448

Text #18

Max Range: 3.1295. Min Range: -3.1295

Max Act: 2.9816. Min Act: -0.1700

Data Index: 1931631 (Open Web Text)

Max Activating Token Index: 152

Text #19

Max Range: 3.1295. Min Range: -3.1295

Max Act: 2.9907. Min Act: -0.1700

Data Index: 4730340 (Open Web Text)

Max Activating Token Index: 322