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

Dataset: Open Web Text

Neuron 2432 in Layer 4

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: 3.7721. Min Range: -3.7721

Max Act: 3.7721. Min Act: -0.1700

Data Index: 6753434 (Open Web Text)

Max Activating Token Index: 851

Text #1

Max Range: 3.7721. Min Range: -3.7721

Max Act: 3.5465. Min Act: -0.1700

Data Index: 3180039 (Open Web Text)

Max Activating Token Index: 416

Text #2

Max Range: 3.7721. Min Range: -3.7721

Max Act: 3.5157. Min Act: -0.1700

Data Index: 2107756 (Open Web Text)

Max Activating Token Index: 456

Text #3

Max Range: 3.7721. Min Range: -3.7721

Max Act: 3.5324. Min Act: -0.1700

Data Index: 2187774 (Open Web Text)

Max Activating Token Index: 840

Text #4

Max Range: 3.7721. Min Range: -3.7721

Max Act: 3.4819. Min Act: -0.1700

Data Index: 4959383 (Open Web Text)

Max Activating Token Index: 291

Text #5

Max Range: 3.7721. Min Range: -3.7721

Max Act: 3.4713. Min Act: -0.1700

Data Index: 2004433 (Open Web Text)

Max Activating Token Index: 696

Text #6

Max Range: 3.7721. Min Range: -3.7721

Max Act: 3.4482. Min Act: -0.1700

Data Index: 6040581 (Open Web Text)

Max Activating Token Index: 194

Text #7

Max Range: 3.7721. Min Range: -3.7721

Max Act: 3.4668. Min Act: -0.1700

Data Index: 1277505 (Open Web Text)

Max Activating Token Index: 349

Text #8

Max Range: 3.7721. Min Range: -3.7721

Max Act: 3.4480. Min Act: -0.1700

Data Index: 8822129 (Open Web Text)

Max Activating Token Index: 67

Text #9

Max Range: 3.7721. Min Range: -3.7721

Max Act: 3.4604. Min Act: -0.1700

Data Index: 8385256 (Open Web Text)

Max Activating Token Index: 87

Text #10

Max Range: 3.7721. Min Range: -3.7721

Max Act: 3.4102. Min Act: -0.1700

Data Index: 2760985 (Open Web Text)

Max Activating Token Index: 139

Text #11

Max Range: 3.7721. Min Range: -3.7721

Max Act: 3.4700. Min Act: -0.1700

Data Index: 7807347 (Open Web Text)

Max Activating Token Index: 565

Text #12

Max Range: 3.7721. Min Range: -3.7721

Max Act: 3.3849. Min Act: -0.1700

Data Index: 1773098 (Open Web Text)

Max Activating Token Index: 424

Text #13

Max Range: 3.7721. Min Range: -3.7721

Max Act: 3.4274. Min Act: -0.1700

Data Index: 2180640 (Open Web Text)

Max Activating Token Index: 233

Text #14

Max Range: 3.7721. Min Range: -3.7721

Max Act: 3.3968. Min Act: -0.1700

Data Index: 5754024 (Open Web Text)

Max Activating Token Index: 174

Text #15

Max Range: 3.7721. Min Range: -3.7721

Max Act: 3.3525. Min Act: -0.1700

Data Index: 888444 (Open Web Text)

Max Activating Token Index: 779

Text #16

Max Range: 3.7721. Min Range: -3.7721

Max Act: 3.3883. Min Act: -0.1700

Data Index: 5182148 (Open Web Text)

Max Activating Token Index: 366

Text #17

Max Range: 3.7721. Min Range: -3.7721

Max Act: 3.4101. Min Act: -0.1700

Data Index: 271499 (Open Web Text)

Max Activating Token Index: 650

Text #18

Max Range: 3.7721. Min Range: -3.7721

Max Act: 3.3642. Min Act: -0.1700

Data Index: 2544717 (Open Web Text)

Max Activating Token Index: 462

Text #19

Max Range: 3.7721. Min Range: -3.7721

Max Act: 3.3951. Min Act: -0.1700

Data Index: 3079580 (Open Web Text)

Max Activating Token Index: 512