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

Dataset: Open Web Text

Neuron 1281 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: 1.1688. Min Range: -1.1688

Max Act: 1.1688. Min Act: -0.1219

Data Index: 324808 (Open Web Text)

Max Activating Token Index: 165

Text #1

Max Range: 1.1688. Min Range: -1.1688

Max Act: 1.1565. Min Act: -0.1479

Data Index: 2316975 (Open Web Text)

Max Activating Token Index: 24

Text #2

Max Range: 1.1688. Min Range: -1.1688

Max Act: 1.1662. Min Act: -0.1286

Data Index: 5291935 (Open Web Text)

Max Activating Token Index: 321

Text #3

Max Range: 1.1688. Min Range: -1.1688

Max Act: 1.1604. Min Act: -0.1450

Data Index: 152857 (Open Web Text)

Max Activating Token Index: 896

Text #4

Max Range: 1.1688. Min Range: -1.1688

Max Act: 1.1500. Min Act: -0.1066

Data Index: 3602842 (Open Web Text)

Max Activating Token Index: 445

Text #5

Max Range: 1.1688. Min Range: -1.1688

Max Act: 1.1542. Min Act: -0.1262

Data Index: 2829881 (Open Web Text)

Max Activating Token Index: 315

Text #6

Max Range: 1.1688. Min Range: -1.1688

Max Act: 1.1479. Min Act: -0.1597

Data Index: 8374347 (Open Web Text)

Max Activating Token Index: 185

Text #7

Max Range: 1.1688. Min Range: -1.1688

Max Act: 1.1467. Min Act: -0.1631

Data Index: 2232222 (Open Web Text)

Max Activating Token Index: 21

Text #8

Max Range: 1.1688. Min Range: -1.1688

Max Act: 1.1523. Min Act: -0.1603

Data Index: 8769727 (Open Web Text)

Max Activating Token Index: 451

Text #9

Max Range: 1.1688. Min Range: -1.1688

Max Act: 1.1432. Min Act: -0.1181

Data Index: 1065518 (Open Web Text)

Max Activating Token Index: 286

Text #10

Max Range: 1.1688. Min Range: -1.1688

Max Act: 1.1384. Min Act: -0.1340

Data Index: 4485424 (Open Web Text)

Max Activating Token Index: 37

Text #11

Max Range: 1.1688. Min Range: -1.1688

Max Act: 1.1442. Min Act: -0.1251

Data Index: 8743142 (Open Web Text)

Max Activating Token Index: 222

Text #12

Max Range: 1.1688. Min Range: -1.1688

Max Act: 1.1316. Min Act: -0.0666

Data Index: 6618122 (Open Web Text)

Max Activating Token Index: 443

Text #13

Max Range: 1.1688. Min Range: -1.1688

Max Act: 1.1357. Min Act: -0.1085

Data Index: 1284351 (Open Web Text)

Max Activating Token Index: 234

Text #14

Max Range: 1.1688. Min Range: -1.1688

Max Act: 1.1400. Min Act: -0.1251

Data Index: 2316976 (Open Web Text)

Max Activating Token Index: 326

Text #15

Max Range: 1.1688. Min Range: -1.1688

Max Act: 1.1293. Min Act: -0.1169

Data Index: 8706809 (Open Web Text)

Max Activating Token Index: 410

Text #16

Max Range: 1.1688. Min Range: -1.1688

Max Act: 1.1349. Min Act: -0.1267

Data Index: 5960010 (Open Web Text)

Max Activating Token Index: 816

Text #17

Max Range: 1.1688. Min Range: -1.1688

Max Act: 1.1246. Min Act: -0.1327

Data Index: 4957090 (Open Web Text)

Max Activating Token Index: 703

Text #18

Max Range: 1.1688. Min Range: -1.1688

Max Act: 1.1292. Min Act: -0.1082

Data Index: 8803188 (Open Web Text)

Max Activating Token Index: 632

Text #19

Max Range: 1.1688. Min Range: -1.1688

Max Act: 1.1270. Min Act: -0.1240

Data Index: 3800918 (Open Web Text)

Max Activating Token Index: 338