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

Dataset: Open Web Text

Neuron 2008 in Layer 5

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: 3.2078. Min Range: -3.2078

Max Act: 3.2078. Min Act: -0.1700

Data Index: 2257918 (Open Web Text)

Max Activating Token Index: 183

Text #1

Max Range: 3.2078. Min Range: -3.2078

Max Act: 3.1656. Min Act: -0.1700

Data Index: 1579444 (Open Web Text)

Max Activating Token Index: 30

Text #2

Max Range: 3.2078. Min Range: -3.2078

Max Act: 3.1331. Min Act: -0.1700

Data Index: 6463995 (Open Web Text)

Max Activating Token Index: 433

Text #3

Max Range: 3.2078. Min Range: -3.2078

Max Act: 3.0966. Min Act: -0.1700

Data Index: 2991049 (Open Web Text)

Max Activating Token Index: 200

Text #4

Max Range: 3.2078. Min Range: -3.2078

Max Act: 3.0987. Min Act: -0.1700

Data Index: 14480 (Open Web Text)

Max Activating Token Index: 688

Text #5

Max Range: 3.2078. Min Range: -3.2078

Max Act: 3.0990. Min Act: -0.1700

Data Index: 78360 (Open Web Text)

Max Activating Token Index: 531

Text #6

Max Range: 3.2078. Min Range: -3.2078

Max Act: 3.0843. Min Act: -0.1700

Data Index: 8268908 (Open Web Text)

Max Activating Token Index: 315

Text #7

Max Range: 3.2078. Min Range: -3.2078

Max Act: 3.0601. Min Act: -0.1700

Data Index: 7228410 (Open Web Text)

Max Activating Token Index: 575

Text #8

Max Range: 3.2078. Min Range: -3.2078

Max Act: 3.0647. Min Act: -0.1700

Data Index: 4395072 (Open Web Text)

Max Activating Token Index: 489

Text #9

Max Range: 3.2078. Min Range: -3.2078

Max Act: 3.0683. Min Act: -0.1700

Data Index: 6342536 (Open Web Text)

Max Activating Token Index: 85

Text #10

Max Range: 3.2078. Min Range: -3.2078

Max Act: 3.0694. Min Act: -0.1700

Data Index: 4278374 (Open Web Text)

Max Activating Token Index: 44

Text #11

Max Range: 3.2078. Min Range: -3.2078

Max Act: 3.0758. Min Act: -0.1700

Data Index: 5069833 (Open Web Text)

Max Activating Token Index: 978

Text #12

Max Range: 3.2078. Min Range: -3.2078

Max Act: 3.0791. Min Act: -0.1700

Data Index: 243389 (Open Web Text)

Max Activating Token Index: 40

Text #13

Max Range: 3.2078. Min Range: -3.2078

Max Act: 3.0668. Min Act: -0.1700

Data Index: 5453473 (Open Web Text)

Max Activating Token Index: 74

Text #14

Max Range: 3.2078. Min Range: -3.2078

Max Act: 3.0704. Min Act: -0.1700

Data Index: 2581188 (Open Web Text)

Max Activating Token Index: 432

Text #15

Max Range: 3.2078. Min Range: -3.2078

Max Act: 3.0750. Min Act: -0.1700

Data Index: 8340558 (Open Web Text)

Max Activating Token Index: 824

Text #16

Max Range: 3.2078. Min Range: -3.2078

Max Act: 3.0642. Min Act: -0.1700

Data Index: 7726657 (Open Web Text)

Max Activating Token Index: 176

Text #17

Max Range: 3.2078. Min Range: -3.2078

Max Act: 3.0427. Min Act: -0.1700

Data Index: 2344658 (Open Web Text)

Max Activating Token Index: 369

Text #18

Max Range: 3.2078. Min Range: -3.2078

Max Act: 3.0533. Min Act: -0.1700

Data Index: 5285087 (Open Web Text)

Max Activating Token Index: 613

Text #19

Max Range: 3.2078. Min Range: -3.2078

Max Act: 3.0257. Min Act: -0.1700

Data Index: 4081554 (Open Web Text)

Max Activating Token Index: 630