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

Dataset: Open Web Text

Neuron 2864 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: 1.9231. Min Range: -1.9231

Max Act: 1.9231. Min Act: -0.1700

Data Index: 1049748 (Open Web Text)

Max Activating Token Index: 760

Text #1

Max Range: 1.9231. Min Range: -1.9231

Max Act: 1.9018. Min Act: -0.1699

Data Index: 6864151 (Open Web Text)

Max Activating Token Index: 437

Text #2

Max Range: 1.9231. Min Range: -1.9231

Max Act: 1.9055. Min Act: -0.1700

Data Index: 965075 (Open Web Text)

Max Activating Token Index: 862

Text #3

Max Range: 1.9231. Min Range: -1.9231

Max Act: 1.8881. Min Act: -0.1696

Data Index: 7947611 (Open Web Text)

Max Activating Token Index: 712

Text #4

Max Range: 1.9231. Min Range: -1.9231

Max Act: 1.8783. Min Act: -0.1700

Data Index: 137999 (Open Web Text)

Max Activating Token Index: 517

Text #5

Max Range: 1.9231. Min Range: -1.9231

Max Act: 1.8834. Min Act: -0.1700

Data Index: 8346834 (Open Web Text)

Max Activating Token Index: 807

Text #6

Max Range: 1.9231. Min Range: -1.9231

Max Act: 1.8822. Min Act: -0.1700

Data Index: 5054350 (Open Web Text)

Max Activating Token Index: 294

Text #7

Max Range: 1.9231. Min Range: -1.9231

Max Act: 1.8710. Min Act: -0.1700

Data Index: 7521659 (Open Web Text)

Max Activating Token Index: 384

Text #8

Max Range: 1.9231. Min Range: -1.9231

Max Act: 1.8594. Min Act: -0.1700

Data Index: 8346838 (Open Web Text)

Max Activating Token Index: 300

Text #9

Max Range: 1.9231. Min Range: -1.9231

Max Act: 1.8579. Min Act: -0.1690

Data Index: 2236523 (Open Web Text)

Max Activating Token Index: 372

Text #10

Max Range: 1.9231. Min Range: -1.9231

Max Act: 1.8482. Min Act: -0.1700

Data Index: 1878351 (Open Web Text)

Max Activating Token Index: 234

Text #11

Max Range: 1.9231. Min Range: -1.9231

Max Act: 1.8417. Min Act: -0.1625

Data Index: 5266910 (Open Web Text)

Max Activating Token Index: 815

Text #12

Max Range: 1.9231. Min Range: -1.9231

Max Act: 1.8500. Min Act: -0.1700

Data Index: 46853 (Open Web Text)

Max Activating Token Index: 484

Text #13

Max Range: 1.9231. Min Range: -1.9231

Max Act: 1.8415. Min Act: -0.1700

Data Index: 6623841 (Open Web Text)

Max Activating Token Index: 349

Text #14

Max Range: 1.9231. Min Range: -1.9231

Max Act: 1.8518. Min Act: -0.1700

Data Index: 4591896 (Open Web Text)

Max Activating Token Index: 126

Text #15

Max Range: 1.9231. Min Range: -1.9231

Max Act: 1.8359. Min Act: -0.1700

Data Index: 3370221 (Open Web Text)

Max Activating Token Index: 690

Text #16

Max Range: 1.9231. Min Range: -1.9231

Max Act: 1.8359. Min Act: -0.1700

Data Index: 6643140 (Open Web Text)

Max Activating Token Index: 223

Text #17

Max Range: 1.9231. Min Range: -1.9231

Max Act: 1.8272. Min Act: -0.1676

Data Index: 3049499 (Open Web Text)

Max Activating Token Index: 45

Text #18

Max Range: 1.9231. Min Range: -1.9231

Max Act: 1.8262. Min Act: -0.1699

Data Index: 2727716 (Open Web Text)

Max Activating Token Index: 271

Text #19

Max Range: 1.9231. Min Range: -1.9231

Max Act: 1.8343. Min Act: -0.1700

Data Index: 160517 (Open Web Text)

Max Activating Token Index: 594