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

Dataset: Open Web Text

Neuron 1562 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: 3.6847. Min Range: -3.6847

Max Act: 3.6847. Min Act: -0.1700

Data Index: 649473 (Open Web Text)

Max Activating Token Index: 368

Text #1

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.6076. Min Act: -0.1700

Data Index: 8599538 (Open Web Text)

Max Activating Token Index: 819

Text #2

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.5703. Min Act: -0.1700

Data Index: 644324 (Open Web Text)

Max Activating Token Index: 692

Text #3

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.5360. Min Act: -0.1700

Data Index: 7005076 (Open Web Text)

Max Activating Token Index: 972

Text #4

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.5326. Min Act: -0.1700

Data Index: 7043282 (Open Web Text)

Max Activating Token Index: 16

Text #5

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.5234. Min Act: -0.1700

Data Index: 1516968 (Open Web Text)

Max Activating Token Index: 895

Text #6

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.5095. Min Act: -0.1700

Data Index: 745183 (Open Web Text)

Max Activating Token Index: 21

Text #7

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.4861. Min Act: -0.1700

Data Index: 2829385 (Open Web Text)

Max Activating Token Index: 749

Text #8

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.4446. Min Act: -0.1700

Data Index: 5826833 (Open Web Text)

Max Activating Token Index: 498

Text #9

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.4585. Min Act: -0.1700

Data Index: 2160400 (Open Web Text)

Max Activating Token Index: 747

Text #10

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.4563. Min Act: -0.1700

Data Index: 531586 (Open Web Text)

Max Activating Token Index: 550

Text #11

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.4499. Min Act: -0.1700

Data Index: 770983 (Open Web Text)

Max Activating Token Index: 233

Text #12

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.4630. Min Act: -0.1700

Data Index: 3211169 (Open Web Text)

Max Activating Token Index: 30

Text #13

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.4779. Min Act: -0.1700

Data Index: 1787606 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.4764. Min Act: -0.1700

Data Index: 1438623 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.4734. Min Act: -0.1700

Data Index: 7323220 (Open Web Text)

Max Activating Token Index: 735

Text #16

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.4546. Min Act: -0.1700

Data Index: 2504945 (Open Web Text)

Max Activating Token Index: 701

Text #17

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.4390. Min Act: -0.1700

Data Index: 5163804 (Open Web Text)

Max Activating Token Index: 794

Text #18

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.4374. Min Act: -0.1700

Data Index: 5636101 (Open Web Text)

Max Activating Token Index: 775

Text #19

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.4086. Min Act: -0.1700

Data Index: 5680227 (Open Web Text)

Max Activating Token Index: 678