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

Dataset: Open Web Text

Neuron 881 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: 1.1697. Min Range: -1.1697

Max Act: 1.1697. Min Act: -0.1602

Data Index: 1048003 (Open Web Text)

Max Activating Token Index: 546

Text #1

Max Range: 1.1697. Min Range: -1.1697

Max Act: 1.1557. Min Act: -0.1685

Data Index: 1741596 (Open Web Text)

Max Activating Token Index: 1021

Text #2

Max Range: 1.1697. Min Range: -1.1697

Max Act: 1.1491. Min Act: -0.1470

Data Index: 5027137 (Open Web Text)

Max Activating Token Index: 498

Text #3

Max Range: 1.1697. Min Range: -1.1697

Max Act: 1.1438. Min Act: -0.1675

Data Index: 415265 (Open Web Text)

Max Activating Token Index: 709

Text #4

Max Range: 1.1697. Min Range: -1.1697

Max Act: 1.1376. Min Act: -0.1700

Data Index: 6898487 (Open Web Text)

Max Activating Token Index: 39

Text #5

Max Range: 1.1697. Min Range: -1.1697

Max Act: 1.1291. Min Act: -0.1700

Data Index: 2529049 (Open Web Text)

Max Activating Token Index: 462

Text #6

Max Range: 1.1697. Min Range: -1.1697

Max Act: 1.1230. Min Act: -0.1629

Data Index: 6332872 (Open Web Text)

Max Activating Token Index: 66

Text #7

Max Range: 1.1697. Min Range: -1.1697

Max Act: 1.1214. Min Act: -0.1581

Data Index: 3005209 (Open Web Text)

Max Activating Token Index: 643

Text #8

Max Range: 1.1697. Min Range: -1.1697

Max Act: 1.1203. Min Act: -0.1329

Data Index: 4128648 (Open Web Text)

Max Activating Token Index: 348

Text #9

Max Range: 1.1697. Min Range: -1.1697

Max Act: 1.1226. Min Act: -0.1268

Data Index: 3088412 (Open Web Text)

Max Activating Token Index: 839

Text #10

Max Range: 1.1697. Min Range: -1.1697

Max Act: 1.1229. Min Act: -0.1609

Data Index: 4361446 (Open Web Text)

Max Activating Token Index: 19

Text #11

Max Range: 1.1697. Min Range: -1.1697

Max Act: 1.1256. Min Act: -0.1663

Data Index: 7949933 (Open Web Text)

Max Activating Token Index: 429

Text #12

Max Range: 1.1697. Min Range: -1.1697

Max Act: 1.1229. Min Act: -0.1485

Data Index: 6855464 (Open Web Text)

Max Activating Token Index: 645

Text #13

Max Range: 1.1697. Min Range: -1.1697

Max Act: 1.1086. Min Act: -0.1643

Data Index: 7132099 (Open Web Text)

Max Activating Token Index: 443

Text #14

Max Range: 1.1697. Min Range: -1.1697

Max Act: 1.1143. Min Act: -0.1566

Data Index: 2077124 (Open Web Text)

Max Activating Token Index: 612

Text #15

Max Range: 1.1697. Min Range: -1.1697

Max Act: 1.1085. Min Act: -0.1697

Data Index: 1261037 (Open Web Text)

Max Activating Token Index: 29

Text #16

Max Range: 1.1697. Min Range: -1.1697

Max Act: 1.1032. Min Act: -0.1700

Data Index: 8588234 (Open Web Text)

Max Activating Token Index: 471

Text #17

Max Range: 1.1697. Min Range: -1.1697

Max Act: 1.1132. Min Act: -0.1543

Data Index: 4564504 (Open Web Text)

Max Activating Token Index: 629

Text #18

Max Range: 1.1697. Min Range: -1.1697

Max Act: 1.1023. Min Act: -0.1618

Data Index: 4476495 (Open Web Text)

Max Activating Token Index: 545

Text #19

Max Range: 1.1697. Min Range: -1.1697

Max Act: 1.0976. Min Act: -0.1678

Data Index: 3021255 (Open Web Text)

Max Activating Token Index: 767