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

Dataset: Open Web Text

Neuron 352 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: 6.1501. Min Range: -6.1501

Max Act: 6.1501. Min Act: -0.1683

Data Index: 2466665 (Open Web Text)

Max Activating Token Index: 782

Text #1

Max Range: 6.1501. Min Range: -6.1501

Max Act: 6.1143. Min Act: -0.1691

Data Index: 3168789 (Open Web Text)

Max Activating Token Index: 459

Text #2

Max Range: 6.1501. Min Range: -6.1501

Max Act: 6.0756. Min Act: -0.1700

Data Index: 3192389 (Open Web Text)

Max Activating Token Index: 437

Text #3

Max Range: 6.1501. Min Range: -6.1501

Max Act: 6.0768. Min Act: -0.1456

Data Index: 2298245 (Open Web Text)

Max Activating Token Index: 812

Text #4

Max Range: 6.1501. Min Range: -6.1501

Max Act: 6.0902. Min Act: -0.1700

Data Index: 7931500 (Open Web Text)

Max Activating Token Index: 397

Text #5

Max Range: 6.1501. Min Range: -6.1501

Max Act: 6.0734. Min Act: -0.1700

Data Index: 6003889 (Open Web Text)

Max Activating Token Index: 425

Text #6

Max Range: 6.1501. Min Range: -6.1501

Max Act: 6.0408. Min Act: -0.1700

Data Index: 837701 (Open Web Text)

Max Activating Token Index: 795

Text #7

Max Range: 6.1501. Min Range: -6.1501

Max Act: 6.0332. Min Act: -0.1655

Data Index: 6886545 (Open Web Text)

Max Activating Token Index: 759

Text #8

Max Range: 6.1501. Min Range: -6.1501

Max Act: 6.0283. Min Act: -0.1693

Data Index: 7320427 (Open Web Text)

Max Activating Token Index: 464

Text #9

Max Range: 6.1501. Min Range: -6.1501

Max Act: 6.0033. Min Act: -0.1700

Data Index: 1346725 (Open Web Text)

Max Activating Token Index: 775

Text #10

Max Range: 6.1501. Min Range: -6.1501

Max Act: 5.9797. Min Act: -0.1551

Data Index: 5015971 (Open Web Text)

Max Activating Token Index: 1014

Text #11

Max Range: 6.1501. Min Range: -6.1501

Max Act: 5.9553. Min Act: -0.1684

Data Index: 6144508 (Open Web Text)

Max Activating Token Index: 219

Text #12

Max Range: 6.1501. Min Range: -6.1501

Max Act: 6.0068. Min Act: -0.1685

Data Index: 7437815 (Open Web Text)

Max Activating Token Index: 257

Text #13

Max Range: 6.1501. Min Range: -6.1501

Max Act: 5.9941. Min Act: -0.1691

Data Index: 2863824 (Open Web Text)

Max Activating Token Index: 697

Text #14

Max Range: 6.1501. Min Range: -6.1501

Max Act: 5.9819. Min Act: -0.1700

Data Index: 7398775 (Open Web Text)

Max Activating Token Index: 117

Text #15

Max Range: 6.1501. Min Range: -6.1501

Max Act: 5.9835. Min Act: -0.1700

Data Index: 8370852 (Open Web Text)

Max Activating Token Index: 697

Text #16

Max Range: 6.1501. Min Range: -6.1501

Max Act: 5.9783. Min Act: -0.1699

Data Index: 6298491 (Open Web Text)

Max Activating Token Index: 306

Text #17

Max Range: 6.1501. Min Range: -6.1501

Max Act: 5.9282. Min Act: -0.1689

Data Index: 178432 (Open Web Text)

Max Activating Token Index: 162

Text #18

Max Range: 6.1501. Min Range: -6.1501

Max Act: 5.9616. Min Act: -0.1699

Data Index: 6451091 (Open Web Text)

Max Activating Token Index: 442

Text #19

Max Range: 6.1501. Min Range: -6.1501

Max Act: 5.9522. Min Act: -0.1621

Data Index: 8039433 (Open Web Text)

Max Activating Token Index: 849