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

Dataset: Open Web Text

Neuron 762 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: 1.1865. Min Range: -1.1865

Max Act: 1.1865. Min Act: -0.1574

Data Index: 7566768 (Open Web Text)

Max Activating Token Index: 817

Text #1

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.1376. Min Act: -0.1288

Data Index: 1813860 (Open Web Text)

Max Activating Token Index: 759

Text #2

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.0845. Min Act: -0.1416

Data Index: 2654464 (Open Web Text)

Max Activating Token Index: 1019

Text #3

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.0697. Min Act: -0.1382

Data Index: 1253395 (Open Web Text)

Max Activating Token Index: 944

Text #4

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.0612. Min Act: -0.1419

Data Index: 5230497 (Open Web Text)

Max Activating Token Index: 327

Text #5

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.0646. Min Act: -0.1328

Data Index: 4456371 (Open Web Text)

Max Activating Token Index: 168

Text #6

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.0532. Min Act: -0.1415

Data Index: 479624 (Open Web Text)

Max Activating Token Index: 1022

Text #7

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.0561. Min Act: -0.1406

Data Index: 6720765 (Open Web Text)

Max Activating Token Index: 729

Text #8

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.0421. Min Act: -0.1435

Data Index: 407705 (Open Web Text)

Max Activating Token Index: 985

Text #9

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.0412. Min Act: -0.1627

Data Index: 6902710 (Open Web Text)

Max Activating Token Index: 186

Text #10

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.0436. Min Act: -0.1267

Data Index: 3640843 (Open Web Text)

Max Activating Token Index: 1005

Text #11

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.0384. Min Act: -0.1590

Data Index: 1914575 (Open Web Text)

Max Activating Token Index: 1018

Text #12

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.0286. Min Act: -0.1144

Data Index: 5739928 (Open Web Text)

Max Activating Token Index: 1014

Text #13

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.0171. Min Act: -0.1482

Data Index: 844637 (Open Web Text)

Max Activating Token Index: 361

Text #14

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.0181. Min Act: -0.1489

Data Index: 8254424 (Open Web Text)

Max Activating Token Index: 1019

Text #15

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.0183. Min Act: -0.1183

Data Index: 7933014 (Open Web Text)

Max Activating Token Index: 966

Text #16

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.0180. Min Act: -0.1301

Data Index: 6673417 (Open Web Text)

Max Activating Token Index: 332

Text #17

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.0189. Min Act: -0.1445

Data Index: 8501944 (Open Web Text)

Max Activating Token Index: 822

Text #18

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.0161. Min Act: -0.1340

Data Index: 6709157 (Open Web Text)

Max Activating Token Index: 1012

Text #19

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.0044. Min Act: -0.1621

Data Index: 4385451 (Open Web Text)

Max Activating Token Index: 1021