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

Dataset: Open Web Text

Neuron 2802 in Layer 0

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: 6.2682. Min Range: -6.2682

Max Act: 6.2682. Min Act: -0.1700

Data Index: 8390735 (Open Web Text)

Max Activating Token Index: 888

Text #1

Max Range: 6.2682. Min Range: -6.2682

Max Act: 6.2471. Min Act: -0.1700

Data Index: 4829667 (Open Web Text)

Max Activating Token Index: 364

Text #2

Max Range: 6.2682. Min Range: -6.2682

Max Act: 6.1758. Min Act: -0.1700

Data Index: 3109523 (Open Web Text)

Max Activating Token Index: 357

Text #3

Max Range: 6.2682. Min Range: -6.2682

Max Act: 6.1495. Min Act: -0.1700

Data Index: 3325973 (Open Web Text)

Max Activating Token Index: 909

Text #4

Max Range: 6.2682. Min Range: -6.2682

Max Act: 6.2153. Min Act: -0.1700

Data Index: 8089967 (Open Web Text)

Max Activating Token Index: 364

Text #5

Max Range: 6.2682. Min Range: -6.2682

Max Act: 6.2054. Min Act: -0.1700

Data Index: 517421 (Open Web Text)

Max Activating Token Index: 912

Text #6

Max Range: 6.2682. Min Range: -6.2682

Max Act: 6.1350. Min Act: -0.1700

Data Index: 5150080 (Open Web Text)

Max Activating Token Index: 927

Text #7

Max Range: 6.2682. Min Range: -6.2682

Max Act: 6.1401. Min Act: -0.1700

Data Index: 751813 (Open Web Text)

Max Activating Token Index: 966

Text #8

Max Range: 6.2682. Min Range: -6.2682

Max Act: 6.1526. Min Act: -0.1700

Data Index: 4583550 (Open Web Text)

Max Activating Token Index: 710

Text #9

Max Range: 6.2682. Min Range: -6.2682

Max Act: 6.1264. Min Act: -0.1700

Data Index: 1926053 (Open Web Text)

Max Activating Token Index: 914

Text #10

Max Range: 6.2682. Min Range: -6.2682

Max Act: 6.1473. Min Act: -0.1700

Data Index: 8509975 (Open Web Text)

Max Activating Token Index: 357

Text #11

Max Range: 6.2682. Min Range: -6.2682

Max Act: 6.1700. Min Act: -0.1700

Data Index: 3419285 (Open Web Text)

Max Activating Token Index: 739

Text #12

Max Range: 6.2682. Min Range: -6.2682

Max Act: 6.1350. Min Act: -0.1700

Data Index: 2917404 (Open Web Text)

Max Activating Token Index: 936

Text #13

Max Range: 6.2682. Min Range: -6.2682

Max Act: 6.1562. Min Act: -0.1700

Data Index: 7286070 (Open Web Text)

Max Activating Token Index: 334

Text #14

Max Range: 6.2682. Min Range: -6.2682

Max Act: 6.1855. Min Act: -0.1700

Data Index: 6747394 (Open Web Text)

Max Activating Token Index: 355

Text #15

Max Range: 6.2682. Min Range: -6.2682

Max Act: 6.1508. Min Act: -0.1700

Data Index: 5836979 (Open Web Text)

Max Activating Token Index: 357

Text #16

Max Range: 6.2682. Min Range: -6.2682

Max Act: 6.1433. Min Act: -0.1700

Data Index: 5728816 (Open Web Text)

Max Activating Token Index: 899

Text #17

Max Range: 6.2682. Min Range: -6.2682

Max Act: 6.1679. Min Act: -0.1700

Data Index: 2579053 (Open Web Text)

Max Activating Token Index: 374

Text #18

Max Range: 6.2682. Min Range: -6.2682

Max Act: 6.1574. Min Act: -0.1700

Data Index: 2467806 (Open Web Text)

Max Activating Token Index: 875

Text #19

Max Range: 6.2682. Min Range: -6.2682

Max Act: 6.1163. Min Act: -0.1700

Data Index: 472321 (Open Web Text)

Max Activating Token Index: 946