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

Dataset: Open Web Text

Neuron 2629 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: 1.1551. Min Range: -1.1551

Max Act: 1.1551. Min Act: -0.1644

Data Index: 2468719 (Open Web Text)

Max Activating Token Index: 631

Text #1

Max Range: 1.1551. Min Range: -1.1551

Max Act: 1.1549. Min Act: -0.1659

Data Index: 5635249 (Open Web Text)

Max Activating Token Index: 469

Text #2

Max Range: 1.1551. Min Range: -1.1551

Max Act: 1.1507. Min Act: -0.1686

Data Index: 5150259 (Open Web Text)

Max Activating Token Index: 1019

Text #3

Max Range: 1.1551. Min Range: -1.1551

Max Act: 1.1302. Min Act: -0.1700

Data Index: 6743515 (Open Web Text)

Max Activating Token Index: 993

Text #4

Max Range: 1.1551. Min Range: -1.1551

Max Act: 1.1233. Min Act: -0.1534

Data Index: 8636357 (Open Web Text)

Max Activating Token Index: 646

Text #5

Max Range: 1.1551. Min Range: -1.1551

Max Act: 1.1069. Min Act: -0.1512

Data Index: 254024 (Open Web Text)

Max Activating Token Index: 690

Text #6

Max Range: 1.1551. Min Range: -1.1551

Max Act: 1.1060. Min Act: -0.1625

Data Index: 8613581 (Open Web Text)

Max Activating Token Index: 1022

Text #7

Max Range: 1.1551. Min Range: -1.1551

Max Act: 1.1002. Min Act: -0.1497

Data Index: 4737966 (Open Web Text)

Max Activating Token Index: 357

Text #8

Max Range: 1.1551. Min Range: -1.1551

Max Act: 1.0978. Min Act: -0.1604

Data Index: 169925 (Open Web Text)

Max Activating Token Index: 722

Text #9

Max Range: 1.1551. Min Range: -1.1551

Max Act: 1.1025. Min Act: -0.1698

Data Index: 3367347 (Open Web Text)

Max Activating Token Index: 1012

Text #10

Max Range: 1.1551. Min Range: -1.1551

Max Act: 1.0886. Min Act: -0.1653

Data Index: 2025235 (Open Web Text)

Max Activating Token Index: 1019

Text #11

Max Range: 1.1551. Min Range: -1.1551

Max Act: 1.0998. Min Act: -0.1437

Data Index: 1179373 (Open Web Text)

Max Activating Token Index: 970

Text #12

Max Range: 1.1551. Min Range: -1.1551

Max Act: 1.0955. Min Act: -0.1665

Data Index: 5076636 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 1.1551. Min Range: -1.1551

Max Act: 1.0948. Min Act: -0.1552

Data Index: 1939177 (Open Web Text)

Max Activating Token Index: 1018

Text #14

Max Range: 1.1551. Min Range: -1.1551

Max Act: 1.0908. Min Act: -0.1605

Data Index: 166704 (Open Web Text)

Max Activating Token Index: 724

Text #15

Max Range: 1.1551. Min Range: -1.1551

Max Act: 1.0876. Min Act: -0.1597

Data Index: 4004241 (Open Web Text)

Max Activating Token Index: 1015

Text #16

Max Range: 1.1551. Min Range: -1.1551

Max Act: 1.0890. Min Act: -0.1685

Data Index: 3843495 (Open Web Text)

Max Activating Token Index: 704

Text #17

Max Range: 1.1551. Min Range: -1.1551

Max Act: 1.0886. Min Act: -0.1693

Data Index: 3361230 (Open Web Text)

Max Activating Token Index: 416

Text #18

Max Range: 1.1551. Min Range: -1.1551

Max Act: 1.0834. Min Act: -0.1537

Data Index: 5479341 (Open Web Text)

Max Activating Token Index: 1012

Text #19

Max Range: 1.1551. Min Range: -1.1551

Max Act: 1.0855. Min Act: -0.1654

Data Index: 3701894 (Open Web Text)

Max Activating Token Index: 976