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

Dataset: Open Web Text

Neuron 615 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: 3.2160. Min Range: -3.2160

Max Act: 3.2140. Min Act: -0.1700

Data Index: 7507669 (Open Web Text)

Max Activating Token Index: 906

Text #1

Max Range: 3.2160. Min Range: -3.2160

Max Act: 3.2160. Min Act: -0.1700

Data Index: 8431237 (Open Web Text)

Max Activating Token Index: 811

Text #2

Max Range: 3.2160. Min Range: -3.2160

Max Act: 3.1090. Min Act: -0.1700

Data Index: 6509797 (Open Web Text)

Max Activating Token Index: 325

Text #3

Max Range: 3.2160. Min Range: -3.2160

Max Act: 3.1430. Min Act: -0.1700

Data Index: 261109 (Open Web Text)

Max Activating Token Index: 356

Text #4

Max Range: 3.2160. Min Range: -3.2160

Max Act: 3.1558. Min Act: -0.1700

Data Index: 47300 (Open Web Text)

Max Activating Token Index: 559

Text #5

Max Range: 3.2160. Min Range: -3.2160

Max Act: 3.0660. Min Act: -0.1700

Data Index: 6873194 (Open Web Text)

Max Activating Token Index: 564

Text #6

Max Range: 3.2160. Min Range: -3.2160

Max Act: 3.0972. Min Act: -0.1700

Data Index: 4748234 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.2160. Min Range: -3.2160

Max Act: 3.0899. Min Act: -0.1700

Data Index: 7202323 (Open Web Text)

Max Activating Token Index: 29

Text #8

Max Range: 3.2160. Min Range: -3.2160

Max Act: 3.0696. Min Act: -0.1700

Data Index: 3616504 (Open Web Text)

Max Activating Token Index: 838

Text #9

Max Range: 3.2160. Min Range: -3.2160

Max Act: 3.0710. Min Act: -0.1700

Data Index: 284054 (Open Web Text)

Max Activating Token Index: 91

Text #10

Max Range: 3.2160. Min Range: -3.2160

Max Act: 3.0711. Min Act: -0.1700

Data Index: 7018099 (Open Web Text)

Max Activating Token Index: 325

Text #11

Max Range: 3.2160. Min Range: -3.2160

Max Act: 3.0348. Min Act: -0.1700

Data Index: 780692 (Open Web Text)

Max Activating Token Index: 191

Text #12

Max Range: 3.2160. Min Range: -3.2160

Max Act: 3.0581. Min Act: -0.1700

Data Index: 1273949 (Open Web Text)

Max Activating Token Index: 546

Text #13

Max Range: 3.2160. Min Range: -3.2160

Max Act: 3.0705. Min Act: -0.1700

Data Index: 5337509 (Open Web Text)

Max Activating Token Index: 255

Text #14

Max Range: 3.2160. Min Range: -3.2160

Max Act: 3.1012. Min Act: -0.1700

Data Index: 7847655 (Open Web Text)

Max Activating Token Index: 924

Text #15

Max Range: 3.2160. Min Range: -3.2160

Max Act: 3.0792. Min Act: -0.1700

Data Index: 4462837 (Open Web Text)

Max Activating Token Index: 382

Text #16

Max Range: 3.2160. Min Range: -3.2160

Max Act: 3.0766. Min Act: -0.1700

Data Index: 715041 (Open Web Text)

Max Activating Token Index: 26

Text #17

Max Range: 3.2160. Min Range: -3.2160

Max Act: 3.0943. Min Act: -0.1700

Data Index: 4509435 (Open Web Text)

Max Activating Token Index: 620

Text #18

Max Range: 3.2160. Min Range: -3.2160

Max Act: 3.0579. Min Act: -0.1700

Data Index: 2271752 (Open Web Text)

Max Activating Token Index: 553

Text #19

Max Range: 3.2160. Min Range: -3.2160

Max Act: 3.0684. Min Act: -0.1700

Data Index: 5551955 (Open Web Text)

Max Activating Token Index: 609