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

Dataset: Open Web Text

Neuron 2577 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: 8.9010. Min Range: -8.9010

Max Act: 8.8326. Min Act: -0.1700

Data Index: 6596457 (Open Web Text)

Max Activating Token Index: 352

Text #1

Max Range: 8.9010. Min Range: -8.9010

Max Act: 8.9010. Min Act: -0.1700

Data Index: 7605480 (Open Web Text)

Max Activating Token Index: 806

Text #2

Max Range: 8.9010. Min Range: -8.9010

Max Act: 8.7603. Min Act: -0.1700

Data Index: 3105867 (Open Web Text)

Max Activating Token Index: 395

Text #3

Max Range: 8.9010. Min Range: -8.9010

Max Act: 8.7101. Min Act: -0.1700

Data Index: 757878 (Open Web Text)

Max Activating Token Index: 86

Text #4

Max Range: 8.9010. Min Range: -8.9010

Max Act: 8.6426. Min Act: -0.1700

Data Index: 7084664 (Open Web Text)

Max Activating Token Index: 357

Text #5

Max Range: 8.9010. Min Range: -8.9010

Max Act: 8.6836. Min Act: -0.1700

Data Index: 3434964 (Open Web Text)

Max Activating Token Index: 261

Text #6

Max Range: 8.9010. Min Range: -8.9010

Max Act: 8.6937. Min Act: -0.1700

Data Index: 6225808 (Open Web Text)

Max Activating Token Index: 295

Text #7

Max Range: 8.9010. Min Range: -8.9010

Max Act: 8.7123. Min Act: -0.1700

Data Index: 2981683 (Open Web Text)

Max Activating Token Index: 858

Text #8

Max Range: 8.9010. Min Range: -8.9010

Max Act: 8.6759. Min Act: -0.1700

Data Index: 2773234 (Open Web Text)

Max Activating Token Index: 783

Text #9

Max Range: 8.9010. Min Range: -8.9010

Max Act: 8.6675. Min Act: -0.1700

Data Index: 4842372 (Open Web Text)

Max Activating Token Index: 472

Text #10

Max Range: 8.9010. Min Range: -8.9010

Max Act: 8.6735. Min Act: -0.1700

Data Index: 4757431 (Open Web Text)

Max Activating Token Index: 720

Text #11

Max Range: 8.9010. Min Range: -8.9010

Max Act: 8.7001. Min Act: -0.1700

Data Index: 1675653 (Open Web Text)

Max Activating Token Index: 346

Text #12

Max Range: 8.9010. Min Range: -8.9010

Max Act: 8.6844. Min Act: -0.1700

Data Index: 3745923 (Open Web Text)

Max Activating Token Index: 731

Text #13

Max Range: 8.9010. Min Range: -8.9010

Max Act: 8.6778. Min Act: -0.1700

Data Index: 7130201 (Open Web Text)

Max Activating Token Index: 862

Text #14

Max Range: 8.9010. Min Range: -8.9010

Max Act: 8.6147. Min Act: -0.1700

Data Index: 5234482 (Open Web Text)

Max Activating Token Index: 221

Text #15

Max Range: 8.9010. Min Range: -8.9010

Max Act: 8.5950. Min Act: -0.1700

Data Index: 5532247 (Open Web Text)

Max Activating Token Index: 443

Text #16

Max Range: 8.9010. Min Range: -8.9010

Max Act: 8.5972. Min Act: -0.1700

Data Index: 5801691 (Open Web Text)

Max Activating Token Index: 512

Text #17

Max Range: 8.9010. Min Range: -8.9010

Max Act: 8.5937. Min Act: -0.1700

Data Index: 2134729 (Open Web Text)

Max Activating Token Index: 513

Text #18

Max Range: 8.9010. Min Range: -8.9010

Max Act: 8.6050. Min Act: -0.1700

Data Index: 6258682 (Open Web Text)

Max Activating Token Index: 226

Text #19

Max Range: 8.9010. Min Range: -8.9010

Max Act: 8.6021. Min Act: -0.1700

Data Index: 6459199 (Open Web Text)

Max Activating Token Index: 565