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

Dataset: Open Web Text

Neuron 564 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: 1.2293. Min Range: -1.2293

Max Act: 1.2293. Min Act: -0.1601

Data Index: 3248241 (Open Web Text)

Max Activating Token Index: 960

Text #1

Max Range: 1.2293. Min Range: -1.2293

Max Act: 1.2044. Min Act: -0.1634

Data Index: 7514952 (Open Web Text)

Max Activating Token Index: 246

Text #2

Max Range: 1.2293. Min Range: -1.2293

Max Act: 1.2068. Min Act: -0.1532

Data Index: 5756034 (Open Web Text)

Max Activating Token Index: 216

Text #3

Max Range: 1.2293. Min Range: -1.2293

Max Act: 1.1867. Min Act: -0.1700

Data Index: 8329038 (Open Web Text)

Max Activating Token Index: 222

Text #4

Max Range: 1.2293. Min Range: -1.2293

Max Act: 1.1845. Min Act: -0.1496

Data Index: 5841171 (Open Web Text)

Max Activating Token Index: 150

Text #5

Max Range: 1.2293. Min Range: -1.2293

Max Act: 1.1791. Min Act: -0.1472

Data Index: 4028838 (Open Web Text)

Max Activating Token Index: 201

Text #6

Max Range: 1.2293. Min Range: -1.2293

Max Act: 1.1801. Min Act: -0.1700

Data Index: 6800107 (Open Web Text)

Max Activating Token Index: 216

Text #7

Max Range: 1.2293. Min Range: -1.2293

Max Act: 1.1796. Min Act: -0.1700

Data Index: 7501593 (Open Web Text)

Max Activating Token Index: 179

Text #8

Max Range: 1.2293. Min Range: -1.2293

Max Act: 1.1699. Min Act: -0.1384

Data Index: 2011106 (Open Web Text)

Max Activating Token Index: 935

Text #9

Max Range: 1.2293. Min Range: -1.2293

Max Act: 1.1613. Min Act: -0.1699

Data Index: 1929946 (Open Web Text)

Max Activating Token Index: 271

Text #10

Max Range: 1.2293. Min Range: -1.2293

Max Act: 1.1571. Min Act: -0.1465

Data Index: 437977 (Open Web Text)

Max Activating Token Index: 840

Text #11

Max Range: 1.2293. Min Range: -1.2293

Max Act: 1.1509. Min Act: -0.1614

Data Index: 5998479 (Open Web Text)

Max Activating Token Index: 216

Text #12

Max Range: 1.2293. Min Range: -1.2293

Max Act: 1.1512. Min Act: -0.1692

Data Index: 1651433 (Open Web Text)

Max Activating Token Index: 772

Text #13

Max Range: 1.2293. Min Range: -1.2293

Max Act: 1.1511. Min Act: -0.1699

Data Index: 7840695 (Open Web Text)

Max Activating Token Index: 231

Text #14

Max Range: 1.2293. Min Range: -1.2293

Max Act: 1.1473. Min Act: -0.1524

Data Index: 7828729 (Open Web Text)

Max Activating Token Index: 463

Text #15

Max Range: 1.2293. Min Range: -1.2293

Max Act: 1.1383. Min Act: -0.1696

Data Index: 3695441 (Open Web Text)

Max Activating Token Index: 249

Text #16

Max Range: 1.2293. Min Range: -1.2293

Max Act: 1.1378. Min Act: -0.1700

Data Index: 53034 (Open Web Text)

Max Activating Token Index: 206

Text #17

Max Range: 1.2293. Min Range: -1.2293

Max Act: 1.1455. Min Act: -0.1688

Data Index: 6230141 (Open Web Text)

Max Activating Token Index: 238

Text #18

Max Range: 1.2293. Min Range: -1.2293

Max Act: 1.1445. Min Act: -0.1667

Data Index: 5131986 (Open Web Text)

Max Activating Token Index: 752

Text #19

Max Range: 1.2293. Min Range: -1.2293

Max Act: 1.1380. Min Act: -0.1686

Data Index: 2920241 (Open Web Text)

Max Activating Token Index: 184