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

Dataset: Open Web Text

Neuron 2334 in Layer 0

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: 1.9352. Min Range: -1.9352

Max Act: 1.9352. Min Act: -0.1700

Data Index: 2998988 (Open Web Text)

Max Activating Token Index: 25

Text #1

Max Range: 1.9352. Min Range: -1.9352

Max Act: 1.8551. Min Act: -0.1657

Data Index: 7794196 (Open Web Text)

Max Activating Token Index: 882

Text #2

Max Range: 1.9352. Min Range: -1.9352

Max Act: 1.8630. Min Act: -0.1597

Data Index: 1943343 (Open Web Text)

Max Activating Token Index: 839

Text #3

Max Range: 1.9352. Min Range: -1.9352

Max Act: 1.8197. Min Act: -0.1500

Data Index: 1438438 (Open Web Text)

Max Activating Token Index: 248

Text #4

Max Range: 1.9352. Min Range: -1.9352

Max Act: 1.8127. Min Act: -0.1700

Data Index: 286522 (Open Web Text)

Max Activating Token Index: 49

Text #5

Max Range: 1.9352. Min Range: -1.9352

Max Act: 1.8054. Min Act: -0.1462

Data Index: 652583 (Open Web Text)

Max Activating Token Index: 501

Text #6

Max Range: 1.9352. Min Range: -1.9352

Max Act: 1.7957. Min Act: -0.1583

Data Index: 7922978 (Open Web Text)

Max Activating Token Index: 34

Text #7

Max Range: 1.9352. Min Range: -1.9352

Max Act: 1.7995. Min Act: -0.1319

Data Index: 7082381 (Open Web Text)

Max Activating Token Index: 343

Text #8

Max Range: 1.9352. Min Range: -1.9352

Max Act: 1.7824. Min Act: -0.1699

Data Index: 7954810 (Open Web Text)

Max Activating Token Index: 213

Text #9

Max Range: 1.9352. Min Range: -1.9352

Max Act: 1.7850. Min Act: -0.1564

Data Index: 3987739 (Open Web Text)

Max Activating Token Index: 836

Text #10

Max Range: 1.9352. Min Range: -1.9352

Max Act: 1.7744. Min Act: -0.1458

Data Index: 6997473 (Open Web Text)

Max Activating Token Index: 634

Text #11

Max Range: 1.9352. Min Range: -1.9352

Max Act: 1.7750. Min Act: -0.1680

Data Index: 1356927 (Open Web Text)

Max Activating Token Index: 919

Text #12

Max Range: 1.9352. Min Range: -1.9352

Max Act: 1.7713. Min Act: -0.1663

Data Index: 3187430 (Open Web Text)

Max Activating Token Index: 246

Text #13

Max Range: 1.9352. Min Range: -1.9352

Max Act: 1.7496. Min Act: -0.1245

Data Index: 652581 (Open Web Text)

Max Activating Token Index: 1016

Text #14

Max Range: 1.9352. Min Range: -1.9352

Max Act: 1.7596. Min Act: -0.1655

Data Index: 2844681 (Open Web Text)

Max Activating Token Index: 256

Text #15

Max Range: 1.9352. Min Range: -1.9352

Max Act: 1.7530. Min Act: -0.1483

Data Index: 7410485 (Open Web Text)

Max Activating Token Index: 325

Text #16

Max Range: 1.9352. Min Range: -1.9352

Max Act: 1.7514. Min Act: -0.1668

Data Index: 2931013 (Open Web Text)

Max Activating Token Index: 20

Text #17

Max Range: 1.9352. Min Range: -1.9352

Max Act: 1.7559. Min Act: -0.1664

Data Index: 1728841 (Open Web Text)

Max Activating Token Index: 899

Text #18

Max Range: 1.9352. Min Range: -1.9352

Max Act: 1.7390. Min Act: -0.1700

Data Index: 3764427 (Open Web Text)

Max Activating Token Index: 416

Text #19

Max Range: 1.9352. Min Range: -1.9352

Max Act: 1.7457. Min Act: -0.1480

Data Index: 4913328 (Open Web Text)

Max Activating Token Index: 12