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

Dataset: Open Web Text

Neuron 2422 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: 1.7729. Min Range: -1.7729

Max Act: 1.7729. Min Act: -0.1699

Data Index: 3482750 (Open Web Text)

Max Activating Token Index: 655

Text #1

Max Range: 1.7729. Min Range: -1.7729

Max Act: 1.7728. Min Act: -0.1700

Data Index: 2920066 (Open Web Text)

Max Activating Token Index: 271

Text #2

Max Range: 1.7729. Min Range: -1.7729

Max Act: 1.7612. Min Act: -0.1700

Data Index: 6107180 (Open Web Text)

Max Activating Token Index: 386

Text #3

Max Range: 1.7729. Min Range: -1.7729

Max Act: 1.7668. Min Act: -0.1700

Data Index: 7949087 (Open Web Text)

Max Activating Token Index: 633

Text #4

Max Range: 1.7729. Min Range: -1.7729

Max Act: 1.7641. Min Act: -0.1700

Data Index: 8451391 (Open Web Text)

Max Activating Token Index: 262

Text #5

Max Range: 1.7729. Min Range: -1.7729

Max Act: 1.7488. Min Act: -0.1694

Data Index: 3233911 (Open Web Text)

Max Activating Token Index: 115

Text #6

Max Range: 1.7729. Min Range: -1.7729

Max Act: 1.7451. Min Act: -0.1700

Data Index: 8649771 (Open Web Text)

Max Activating Token Index: 717

Text #7

Max Range: 1.7729. Min Range: -1.7729

Max Act: 1.7383. Min Act: -0.1688

Data Index: 2584389 (Open Web Text)

Max Activating Token Index: 279

Text #8

Max Range: 1.7729. Min Range: -1.7729

Max Act: 1.7381. Min Act: -0.1700

Data Index: 8237327 (Open Web Text)

Max Activating Token Index: 129

Text #9

Max Range: 1.7729. Min Range: -1.7729

Max Act: 1.7244. Min Act: -0.1700

Data Index: 2037696 (Open Web Text)

Max Activating Token Index: 438

Text #10

Max Range: 1.7729. Min Range: -1.7729

Max Act: 1.7235. Min Act: -0.1695

Data Index: 7835384 (Open Web Text)

Max Activating Token Index: 228

Text #11

Max Range: 1.7729. Min Range: -1.7729

Max Act: 1.7287. Min Act: -0.1697

Data Index: 8767992 (Open Web Text)

Max Activating Token Index: 474

Text #12

Max Range: 1.7729. Min Range: -1.7729

Max Act: 1.7204. Min Act: -0.1700

Data Index: 2962922 (Open Web Text)

Max Activating Token Index: 1001

Text #13

Max Range: 1.7729. Min Range: -1.7729

Max Act: 1.7202. Min Act: -0.1698

Data Index: 8500025 (Open Web Text)

Max Activating Token Index: 182

Text #14

Max Range: 1.7729. Min Range: -1.7729

Max Act: 1.7194. Min Act: -0.1699

Data Index: 6931571 (Open Web Text)

Max Activating Token Index: 294

Text #15

Max Range: 1.7729. Min Range: -1.7729

Max Act: 1.7290. Min Act: -0.1700

Data Index: 5199235 (Open Web Text)

Max Activating Token Index: 154

Text #16

Max Range: 1.7729. Min Range: -1.7729

Max Act: 1.7129. Min Act: -0.1700

Data Index: 8724450 (Open Web Text)

Max Activating Token Index: 668

Text #17

Max Range: 1.7729. Min Range: -1.7729

Max Act: 1.7180. Min Act: -0.1700

Data Index: 1875833 (Open Web Text)

Max Activating Token Index: 801

Text #18

Max Range: 1.7729. Min Range: -1.7729

Max Act: 1.7141. Min Act: -0.1700

Data Index: 3994794 (Open Web Text)

Max Activating Token Index: 643

Text #19

Max Range: 1.7729. Min Range: -1.7729

Max Act: 1.7258. Min Act: -0.1700

Data Index: 5823340 (Open Web Text)

Max Activating Token Index: 871