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

Dataset: Open Web Text

Neuron 872 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: 1.7848. Min Range: -1.7848

Max Act: 1.7848. Min Act: -0.1699

Data Index: 4300269 (Open Web Text)

Max Activating Token Index: 838

Text #1

Max Range: 1.7848. Min Range: -1.7848

Max Act: 1.7343. Min Act: -0.1691

Data Index: 1042163 (Open Web Text)

Max Activating Token Index: 536

Text #2

Max Range: 1.7848. Min Range: -1.7848

Max Act: 1.7006. Min Act: -0.1700

Data Index: 1178404 (Open Web Text)

Max Activating Token Index: 759

Text #3

Max Range: 1.7848. Min Range: -1.7848

Max Act: 1.7118. Min Act: -0.1700

Data Index: 5078160 (Open Web Text)

Max Activating Token Index: 800

Text #4

Max Range: 1.7848. Min Range: -1.7848

Max Act: 1.7012. Min Act: -0.1700

Data Index: 1788666 (Open Web Text)

Max Activating Token Index: 19

Text #5

Max Range: 1.7848. Min Range: -1.7848

Max Act: 1.6827. Min Act: -0.1682

Data Index: 4534606 (Open Web Text)

Max Activating Token Index: 960

Text #6

Max Range: 1.7848. Min Range: -1.7848

Max Act: 1.6924. Min Act: -0.1700

Data Index: 1220372 (Open Web Text)

Max Activating Token Index: 46

Text #7

Max Range: 1.7848. Min Range: -1.7848

Max Act: 1.6941. Min Act: -0.1700

Data Index: 4551550 (Open Web Text)

Max Activating Token Index: 500

Text #8

Max Range: 1.7848. Min Range: -1.7848

Max Act: 1.6806. Min Act: -0.1700

Data Index: 1766208 (Open Web Text)

Max Activating Token Index: 129

Text #9

Max Range: 1.7848. Min Range: -1.7848

Max Act: 1.6734. Min Act: -0.1700

Data Index: 817191 (Open Web Text)

Max Activating Token Index: 204

Text #10

Max Range: 1.7848. Min Range: -1.7848

Max Act: 1.6750. Min Act: -0.1700

Data Index: 816063 (Open Web Text)

Max Activating Token Index: 18

Text #11

Max Range: 1.7848. Min Range: -1.7848

Max Act: 1.6768. Min Act: -0.1699

Data Index: 6350553 (Open Web Text)

Max Activating Token Index: 27

Text #12

Max Range: 1.7848. Min Range: -1.7848

Max Act: 1.6732. Min Act: -0.1679

Data Index: 4770657 (Open Web Text)

Max Activating Token Index: 164

Text #13

Max Range: 1.7848. Min Range: -1.7848

Max Act: 1.6775. Min Act: -0.1700

Data Index: 1042162 (Open Web Text)

Max Activating Token Index: 562

Text #14

Max Range: 1.7848. Min Range: -1.7848

Max Act: 1.6548. Min Act: -0.1697

Data Index: 7713341 (Open Web Text)

Max Activating Token Index: 976

Text #15

Max Range: 1.7848. Min Range: -1.7848

Max Act: 1.6564. Min Act: -0.1700

Data Index: 2302998 (Open Web Text)

Max Activating Token Index: 402

Text #16

Max Range: 1.7848. Min Range: -1.7848

Max Act: 1.6624. Min Act: -0.1696

Data Index: 8382207 (Open Web Text)

Max Activating Token Index: 132

Text #17

Max Range: 1.7848. Min Range: -1.7848

Max Act: 1.6588. Min Act: -0.1691

Data Index: 3849885 (Open Web Text)

Max Activating Token Index: 83

Text #18

Max Range: 1.7848. Min Range: -1.7848

Max Act: 1.6607. Min Act: -0.1692

Data Index: 5569258 (Open Web Text)

Max Activating Token Index: 200

Text #19

Max Range: 1.7848. Min Range: -1.7848

Max Act: 1.6419. Min Act: -0.1632

Data Index: 554809 (Open Web Text)

Max Activating Token Index: 940