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

Dataset: Open Web Text

Neuron 687 in Layer 6

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: 3.8470. Min Range: -3.8470

Max Act: 3.8470. Min Act: -0.1700

Data Index: 4131667 (Open Web Text)

Max Activating Token Index: 827

Text #1

Max Range: 3.8470. Min Range: -3.8470

Max Act: 3.8147. Min Act: -0.1700

Data Index: 6224733 (Open Web Text)

Max Activating Token Index: 551

Text #2

Max Range: 3.8470. Min Range: -3.8470

Max Act: 3.7859. Min Act: -0.1700

Data Index: 1659622 (Open Web Text)

Max Activating Token Index: 979

Text #3

Max Range: 3.8470. Min Range: -3.8470

Max Act: 3.6540. Min Act: -0.1700

Data Index: 649745 (Open Web Text)

Max Activating Token Index: 317

Text #4

Max Range: 3.8470. Min Range: -3.8470

Max Act: 3.6563. Min Act: -0.1700

Data Index: 3742125 (Open Web Text)

Max Activating Token Index: 690

Text #5

Max Range: 3.8470. Min Range: -3.8470

Max Act: 3.5673. Min Act: -0.1700

Data Index: 1999785 (Open Web Text)

Max Activating Token Index: 647

Text #6

Max Range: 3.8470. Min Range: -3.8470

Max Act: 3.5772. Min Act: -0.1700

Data Index: 2619735 (Open Web Text)

Max Activating Token Index: 938

Text #7

Max Range: 3.8470. Min Range: -3.8470

Max Act: 3.5357. Min Act: -0.1700

Data Index: 858463 (Open Web Text)

Max Activating Token Index: 544

Text #8

Max Range: 3.8470. Min Range: -3.8470

Max Act: 3.5098. Min Act: -0.1700

Data Index: 4096519 (Open Web Text)

Max Activating Token Index: 522

Text #9

Max Range: 3.8470. Min Range: -3.8470

Max Act: 3.4496. Min Act: -0.1700

Data Index: 3930008 (Open Web Text)

Max Activating Token Index: 1016

Text #10

Max Range: 3.8470. Min Range: -3.8470

Max Act: 3.4801. Min Act: -0.1700

Data Index: 7014004 (Open Web Text)

Max Activating Token Index: 973

Text #11

Max Range: 3.8470. Min Range: -3.8470

Max Act: 3.4561. Min Act: -0.1700

Data Index: 2673679 (Open Web Text)

Max Activating Token Index: 559

Text #12

Max Range: 3.8470. Min Range: -3.8470

Max Act: 3.4305. Min Act: -0.1700

Data Index: 4660157 (Open Web Text)

Max Activating Token Index: 593

Text #13

Max Range: 3.8470. Min Range: -3.8470

Max Act: 3.4346. Min Act: -0.1700

Data Index: 6213178 (Open Web Text)

Max Activating Token Index: 703

Text #14

Max Range: 3.8470. Min Range: -3.8470

Max Act: 3.4528. Min Act: -0.1700

Data Index: 1504111 (Open Web Text)

Max Activating Token Index: 1005

Text #15

Max Range: 3.8470. Min Range: -3.8470

Max Act: 3.4350. Min Act: -0.1700

Data Index: 6081205 (Open Web Text)

Max Activating Token Index: 990

Text #16

Max Range: 3.8470. Min Range: -3.8470

Max Act: 3.4352. Min Act: -0.1700

Data Index: 7299804 (Open Web Text)

Max Activating Token Index: 826

Text #17

Max Range: 3.8470. Min Range: -3.8470

Max Act: 3.4313. Min Act: -0.1700

Data Index: 1147112 (Open Web Text)

Max Activating Token Index: 603

Text #18

Max Range: 3.8470. Min Range: -3.8470

Max Act: 3.4089. Min Act: -0.1700

Data Index: 2052596 (Open Web Text)

Max Activating Token Index: 618

Text #19

Max Range: 3.8470. Min Range: -3.8470

Max Act: 3.4139. Min Act: -0.1700

Data Index: 7159966 (Open Web Text)

Max Activating Token Index: 889