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

Dataset: Open Web Text

Neuron 1765 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: 0.8693. Min Range: -0.8693

Max Act: 0.8693. Min Act: -0.1547

Data Index: 3819711 (Open Web Text)

Max Activating Token Index: 21

Text #1

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.8420. Min Act: -0.1650

Data Index: 6672705 (Open Web Text)

Max Activating Token Index: 16

Text #2

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.8371. Min Act: -0.1639

Data Index: 6833315 (Open Web Text)

Max Activating Token Index: 18

Text #3

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.8378. Min Act: -0.1691

Data Index: 3885502 (Open Web Text)

Max Activating Token Index: 797

Text #4

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.8329. Min Act: -0.1590

Data Index: 867625 (Open Web Text)

Max Activating Token Index: 576

Text #5

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.8268. Min Act: -0.1700

Data Index: 5288158 (Open Web Text)

Max Activating Token Index: 924

Text #6

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.8218. Min Act: -0.1690

Data Index: 1878715 (Open Web Text)

Max Activating Token Index: 13

Text #7

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.8236. Min Act: -0.1700

Data Index: 3149546 (Open Web Text)

Max Activating Token Index: 58

Text #8

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.8189. Min Act: -0.1694

Data Index: 4773662 (Open Web Text)

Max Activating Token Index: 46

Text #9

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.8133. Min Act: -0.1700

Data Index: 6539995 (Open Web Text)

Max Activating Token Index: 285

Text #10

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.8104. Min Act: -0.1645

Data Index: 5819541 (Open Web Text)

Max Activating Token Index: 727

Text #11

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.8097. Min Act: -0.1700

Data Index: 5421793 (Open Web Text)

Max Activating Token Index: 54

Text #12

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.8081. Min Act: -0.1681

Data Index: 2491978 (Open Web Text)

Max Activating Token Index: 108

Text #13

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.8032. Min Act: -0.1502

Data Index: 8713941 (Open Web Text)

Max Activating Token Index: 113

Text #14

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.8049. Min Act: -0.1549

Data Index: 6986764 (Open Web Text)

Max Activating Token Index: 36

Text #15

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.8013. Min Act: -0.1607

Data Index: 8464768 (Open Web Text)

Max Activating Token Index: 30

Text #16

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.8074. Min Act: -0.1689

Data Index: 8369183 (Open Web Text)

Max Activating Token Index: 65

Text #17

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.8056. Min Act: -0.1666

Data Index: 4713395 (Open Web Text)

Max Activating Token Index: 518

Text #18

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.8067. Min Act: -0.1695

Data Index: 6654146 (Open Web Text)

Max Activating Token Index: 519

Text #19

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.8042. Min Act: -0.1672

Data Index: 5118053 (Open Web Text)

Max Activating Token Index: 215