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

Dataset: Open Web Text

Neuron 155 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: 1.1629. Min Range: -1.1629

Max Act: 1.1629. Min Act: -0.1443

Data Index: 2105374 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 1.1629. Min Range: -1.1629

Max Act: 1.1509. Min Act: -0.1508

Data Index: 6081492 (Open Web Text)

Max Activating Token Index: 718

Text #2

Max Range: 1.1629. Min Range: -1.1629

Max Act: 1.1398. Min Act: -0.1557

Data Index: 7331444 (Open Web Text)

Max Activating Token Index: 160

Text #3

Max Range: 1.1629. Min Range: -1.1629

Max Act: 1.1468. Min Act: -0.1432

Data Index: 4189992 (Open Web Text)

Max Activating Token Index: 117

Text #4

Max Range: 1.1629. Min Range: -1.1629

Max Act: 1.1378. Min Act: -0.1695

Data Index: 5031233 (Open Web Text)

Max Activating Token Index: 144

Text #5

Max Range: 1.1629. Min Range: -1.1629

Max Act: 1.1403. Min Act: -0.1493

Data Index: 1460276 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 1.1629. Min Range: -1.1629

Max Act: 1.1403. Min Act: -0.1651

Data Index: 4713098 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 1.1629. Min Range: -1.1629

Max Act: 1.1311. Min Act: -0.1509

Data Index: 1698453 (Open Web Text)

Max Activating Token Index: 149

Text #8

Max Range: 1.1629. Min Range: -1.1629

Max Act: 1.1403. Min Act: -0.1485

Data Index: 1787251 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 1.1629. Min Range: -1.1629

Max Act: 1.1232. Min Act: -0.1611

Data Index: 1434690 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 1.1629. Min Range: -1.1629

Max Act: 1.1311. Min Act: -0.1520

Data Index: 3306259 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 1.1629. Min Range: -1.1629

Max Act: 1.1311. Min Act: -0.1394

Data Index: 4948248 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 1.1629. Min Range: -1.1629

Max Act: 1.1311. Min Act: -0.1365

Data Index: 3257936 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 1.1629. Min Range: -1.1629

Max Act: 1.1311. Min Act: -0.1466

Data Index: 4928472 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 1.1629. Min Range: -1.1629

Max Act: 1.1311. Min Act: -0.1288

Data Index: 4887389 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 1.1629. Min Range: -1.1629

Max Act: 1.1311. Min Act: -0.1459

Data Index: 1385562 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 1.1629. Min Range: -1.1629

Max Act: 1.1311. Min Act: -0.1549

Data Index: 6140124 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 1.1629. Min Range: -1.1629

Max Act: 1.1311. Min Act: -0.1199

Data Index: 584616 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 1.1629. Min Range: -1.1629

Max Act: 1.1311. Min Act: -0.1447

Data Index: 4619295 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 1.1629. Min Range: -1.1629

Max Act: 1.1275. Min Act: -0.1365

Data Index: 2150516 (Open Web Text)

Max Activating Token Index: 678