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

Dataset: Open Web Text

Neuron 1346 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: 4.5636. Min Range: -4.5636

Max Act: 4.5636. Min Act: -0.1700

Data Index: 884623 (Open Web Text)

Max Activating Token Index: 783

Text #1

Max Range: 4.5636. Min Range: -4.5636

Max Act: 4.5166. Min Act: -0.1700

Data Index: 3172757 (Open Web Text)

Max Activating Token Index: 689

Text #2

Max Range: 4.5636. Min Range: -4.5636

Max Act: 4.5221. Min Act: -0.1700

Data Index: 8473229 (Open Web Text)

Max Activating Token Index: 559

Text #3

Max Range: 4.5636. Min Range: -4.5636

Max Act: 4.4850. Min Act: -0.1700

Data Index: 2160089 (Open Web Text)

Max Activating Token Index: 817

Text #4

Max Range: 4.5636. Min Range: -4.5636

Max Act: 4.4723. Min Act: -0.1700

Data Index: 1725169 (Open Web Text)

Max Activating Token Index: 593

Text #5

Max Range: 4.5636. Min Range: -4.5636

Max Act: 4.4856. Min Act: -0.1700

Data Index: 5966528 (Open Web Text)

Max Activating Token Index: 870

Text #6

Max Range: 4.5636. Min Range: -4.5636

Max Act: 4.5028. Min Act: -0.1700

Data Index: 8525972 (Open Web Text)

Max Activating Token Index: 880

Text #7

Max Range: 4.5636. Min Range: -4.5636

Max Act: 4.4860. Min Act: -0.1700

Data Index: 8460715 (Open Web Text)

Max Activating Token Index: 558

Text #8

Max Range: 4.5636. Min Range: -4.5636

Max Act: 4.4886. Min Act: -0.1700

Data Index: 322693 (Open Web Text)

Max Activating Token Index: 887

Text #9

Max Range: 4.5636. Min Range: -4.5636

Max Act: 4.4890. Min Act: -0.1700

Data Index: 6020992 (Open Web Text)

Max Activating Token Index: 193

Text #10

Max Range: 4.5636. Min Range: -4.5636

Max Act: 4.4816. Min Act: -0.1700

Data Index: 793897 (Open Web Text)

Max Activating Token Index: 545

Text #11

Max Range: 4.5636. Min Range: -4.5636

Max Act: 4.4401. Min Act: -0.1700

Data Index: 4745608 (Open Web Text)

Max Activating Token Index: 954

Text #12

Max Range: 4.5636. Min Range: -4.5636

Max Act: 4.4710. Min Act: -0.1700

Data Index: 8020808 (Open Web Text)

Max Activating Token Index: 508

Text #13

Max Range: 4.5636. Min Range: -4.5636

Max Act: 4.4622. Min Act: -0.1700

Data Index: 4933415 (Open Web Text)

Max Activating Token Index: 545

Text #14

Max Range: 4.5636. Min Range: -4.5636

Max Act: 4.4670. Min Act: -0.1700

Data Index: 4989029 (Open Web Text)

Max Activating Token Index: 607

Text #15

Max Range: 4.5636. Min Range: -4.5636

Max Act: 4.4526. Min Act: -0.1700

Data Index: 3388908 (Open Web Text)

Max Activating Token Index: 663

Text #16

Max Range: 4.5636. Min Range: -4.5636

Max Act: 4.4566. Min Act: -0.1700

Data Index: 5150176 (Open Web Text)

Max Activating Token Index: 655

Text #17

Max Range: 4.5636. Min Range: -4.5636

Max Act: 4.4553. Min Act: -0.1700

Data Index: 7571024 (Open Web Text)

Max Activating Token Index: 530

Text #18

Max Range: 4.5636. Min Range: -4.5636

Max Act: 4.4576. Min Act: -0.1700

Data Index: 6868724 (Open Web Text)

Max Activating Token Index: 753

Text #19

Max Range: 4.5636. Min Range: -4.5636

Max Act: 4.4477. Min Act: -0.1700

Data Index: 1705635 (Open Web Text)

Max Activating Token Index: 621