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

Dataset: Open Web Text

Neuron 1382 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: 0.0411. Min Range: -0.0411

Max Act: 0.0411. Min Act: -0.1684

Data Index: 5230135 (Open Web Text)

Max Activating Token Index: 951

Text #1

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0344. Min Act: -0.1700

Data Index: 4114861 (Open Web Text)

Max Activating Token Index: 919

Text #2

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0271. Min Act: -0.1700

Data Index: 3920246 (Open Web Text)

Max Activating Token Index: 935

Text #3

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0294. Min Act: -0.1695

Data Index: 4162728 (Open Web Text)

Max Activating Token Index: 811

Text #4

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0304. Min Act: -0.1697

Data Index: 8511571 (Open Web Text)

Max Activating Token Index: 984

Text #5

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0228. Min Act: -0.1645

Data Index: 4579923 (Open Web Text)

Max Activating Token Index: 919

Text #6

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0143. Min Act: -0.1700

Data Index: 5475470 (Open Web Text)

Max Activating Token Index: 854

Text #7

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0136. Min Act: -0.1619

Data Index: 2326183 (Open Web Text)

Max Activating Token Index: 921

Text #8

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0142. Min Act: -0.1645

Data Index: 1878321 (Open Web Text)

Max Activating Token Index: 943

Text #9

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0115. Min Act: -0.1639

Data Index: 2850798 (Open Web Text)

Max Activating Token Index: 620

Text #10

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0131. Min Act: -0.1699

Data Index: 3353149 (Open Web Text)

Max Activating Token Index: 930

Text #11

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0107. Min Act: -0.1662

Data Index: 4363519 (Open Web Text)

Max Activating Token Index: 936

Text #12

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0114. Min Act: -0.1698

Data Index: 4563473 (Open Web Text)

Max Activating Token Index: 988

Text #13

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0129. Min Act: -0.1700

Data Index: 1818809 (Open Web Text)

Max Activating Token Index: 956

Text #14

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0120. Min Act: -0.1668

Data Index: 7470503 (Open Web Text)

Max Activating Token Index: 913

Text #15

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0068. Min Act: -0.1677

Data Index: 6845014 (Open Web Text)

Max Activating Token Index: 740

Text #16

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0047. Min Act: -0.1587

Data Index: 1787351 (Open Web Text)

Max Activating Token Index: 894

Text #17

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0041. Min Act: -0.1690

Data Index: 6238701 (Open Web Text)

Max Activating Token Index: 875

Text #18

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0038. Min Act: -0.1668

Data Index: 2385021 (Open Web Text)

Max Activating Token Index: 844

Text #19

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0013. Min Act: -0.1651

Data Index: 3671588 (Open Web Text)

Max Activating Token Index: 1012