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

Dataset: Open Web Text

Neuron 1059 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: 1.5484. Min Range: -1.5484

Max Act: 1.5484. Min Act: -0.1700

Data Index: 6452902 (Open Web Text)

Max Activating Token Index: 35

Text #1

Max Range: 1.5484. Min Range: -1.5484

Max Act: 1.5437. Min Act: -0.1700

Data Index: 7774592 (Open Web Text)

Max Activating Token Index: 603

Text #2

Max Range: 1.5484. Min Range: -1.5484

Max Act: 1.5308. Min Act: -0.1700

Data Index: 3057716 (Open Web Text)

Max Activating Token Index: 766

Text #3

Max Range: 1.5484. Min Range: -1.5484

Max Act: 1.5397. Min Act: -0.1700

Data Index: 6941922 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 1.5484. Min Range: -1.5484

Max Act: 1.5254. Min Act: -0.1700

Data Index: 4449497 (Open Web Text)

Max Activating Token Index: 372

Text #5

Max Range: 1.5484. Min Range: -1.5484

Max Act: 1.5183. Min Act: -0.1700

Data Index: 4586612 (Open Web Text)

Max Activating Token Index: 606

Text #6

Max Range: 1.5484. Min Range: -1.5484

Max Act: 1.5169. Min Act: -0.1700

Data Index: 2131361 (Open Web Text)

Max Activating Token Index: 110

Text #7

Max Range: 1.5484. Min Range: -1.5484

Max Act: 1.5403. Min Act: -0.1700

Data Index: 8429357 (Open Web Text)

Max Activating Token Index: 889

Text #8

Max Range: 1.5484. Min Range: -1.5484

Max Act: 1.4987. Min Act: -0.1700

Data Index: 224022 (Open Web Text)

Max Activating Token Index: 899

Text #9

Max Range: 1.5484. Min Range: -1.5484

Max Act: 1.4944. Min Act: -0.1700

Data Index: 684877 (Open Web Text)

Max Activating Token Index: 732

Text #10

Max Range: 1.5484. Min Range: -1.5484

Max Act: 1.5144. Min Act: -0.1700

Data Index: 6987392 (Open Web Text)

Max Activating Token Index: 1011

Text #11

Max Range: 1.5484. Min Range: -1.5484

Max Act: 1.5001. Min Act: -0.1700

Data Index: 2675255 (Open Web Text)

Max Activating Token Index: 571

Text #12

Max Range: 1.5484. Min Range: -1.5484

Max Act: 1.4866. Min Act: -0.1700

Data Index: 1039280 (Open Web Text)

Max Activating Token Index: 490

Text #13

Max Range: 1.5484. Min Range: -1.5484

Max Act: 1.4854. Min Act: -0.1700

Data Index: 5519723 (Open Web Text)

Max Activating Token Index: 682

Text #14

Max Range: 1.5484. Min Range: -1.5484

Max Act: 1.4927. Min Act: -0.1700

Data Index: 7674813 (Open Web Text)

Max Activating Token Index: 731

Text #15

Max Range: 1.5484. Min Range: -1.5484

Max Act: 1.4831. Min Act: -0.1700

Data Index: 5076810 (Open Web Text)

Max Activating Token Index: 422

Text #16

Max Range: 1.5484. Min Range: -1.5484

Max Act: 1.4691. Min Act: -0.1700

Data Index: 3621849 (Open Web Text)

Max Activating Token Index: 201

Text #17

Max Range: 1.5484. Min Range: -1.5484

Max Act: 1.4727. Min Act: -0.1700

Data Index: 7499129 (Open Web Text)

Max Activating Token Index: 881

Text #18

Max Range: 1.5484. Min Range: -1.5484

Max Act: 1.4822. Min Act: -0.1700

Data Index: 5939239 (Open Web Text)

Max Activating Token Index: 45

Text #19

Max Range: 1.5484. Min Range: -1.5484

Max Act: 1.4754. Min Act: -0.1700

Data Index: 1443604 (Open Web Text)

Max Activating Token Index: 627