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

Dataset: Open Web Text

Neuron 1110 in Layer 3

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: 1.7583. Min Range: -1.7583

Max Act: 1.7583. Min Act: -0.1685

Data Index: 2986610 (Open Web Text)

Max Activating Token Index: 229

Text #1

Max Range: 1.7583. Min Range: -1.7583

Max Act: 1.7192. Min Act: -0.1699

Data Index: 7414644 (Open Web Text)

Max Activating Token Index: 376

Text #2

Max Range: 1.7583. Min Range: -1.7583

Max Act: 1.6988. Min Act: -0.1654

Data Index: 7864067 (Open Web Text)

Max Activating Token Index: 664

Text #3

Max Range: 1.7583. Min Range: -1.7583

Max Act: 1.6665. Min Act: -0.1654

Data Index: 7177060 (Open Web Text)

Max Activating Token Index: 468

Text #4

Max Range: 1.7583. Min Range: -1.7583

Max Act: 1.6667. Min Act: -0.1670

Data Index: 8787527 (Open Web Text)

Max Activating Token Index: 843

Text #5

Max Range: 1.7583. Min Range: -1.7583

Max Act: 1.6686. Min Act: -0.1660

Data Index: 4772812 (Open Web Text)

Max Activating Token Index: 356

Text #6

Max Range: 1.7583. Min Range: -1.7583

Max Act: 1.6788. Min Act: -0.1654

Data Index: 7600148 (Open Web Text)

Max Activating Token Index: 124

Text #7

Max Range: 1.7583. Min Range: -1.7583

Max Act: 1.6785. Min Act: -0.1684

Data Index: 1403792 (Open Web Text)

Max Activating Token Index: 42

Text #8

Max Range: 1.7583. Min Range: -1.7583

Max Act: 1.6497. Min Act: -0.1691

Data Index: 6883052 (Open Web Text)

Max Activating Token Index: 313

Text #9

Max Range: 1.7583. Min Range: -1.7583

Max Act: 1.6424. Min Act: -0.1696

Data Index: 8032975 (Open Web Text)

Max Activating Token Index: 664

Text #10

Max Range: 1.7583. Min Range: -1.7583

Max Act: 1.6498. Min Act: -0.1700

Data Index: 5770405 (Open Web Text)

Max Activating Token Index: 280

Text #11

Max Range: 1.7583. Min Range: -1.7583

Max Act: 1.6236. Min Act: -0.1654

Data Index: 8302072 (Open Web Text)

Max Activating Token Index: 271

Text #12

Max Range: 1.7583. Min Range: -1.7583

Max Act: 1.6215. Min Act: -0.1692

Data Index: 3443650 (Open Web Text)

Max Activating Token Index: 302

Text #13

Max Range: 1.7583. Min Range: -1.7583

Max Act: 1.6450. Min Act: -0.1699

Data Index: 166117 (Open Web Text)

Max Activating Token Index: 607

Text #14

Max Range: 1.7583. Min Range: -1.7583

Max Act: 1.6188. Min Act: -0.1699

Data Index: 8749135 (Open Web Text)

Max Activating Token Index: 454

Text #15

Max Range: 1.7583. Min Range: -1.7583

Max Act: 1.6167. Min Act: -0.1700

Data Index: 4274941 (Open Web Text)

Max Activating Token Index: 632

Text #16

Max Range: 1.7583. Min Range: -1.7583

Max Act: 1.6189. Min Act: -0.1654

Data Index: 4791343 (Open Web Text)

Max Activating Token Index: 1002

Text #17

Max Range: 1.7583. Min Range: -1.7583

Max Act: 1.6254. Min Act: -0.1685

Data Index: 3585003 (Open Web Text)

Max Activating Token Index: 515

Text #18

Max Range: 1.7583. Min Range: -1.7583

Max Act: 1.6196. Min Act: -0.1654

Data Index: 3858998 (Open Web Text)

Max Activating Token Index: 565

Text #19

Max Range: 1.7583. Min Range: -1.7583

Max Act: 1.6063. Min Act: -0.1675

Data Index: 7119700 (Open Web Text)

Max Activating Token Index: 673