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

Dataset: Open Web Text

Neuron 2090 in Layer 2

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: 2.0754. Min Range: -2.0754

Max Act: 2.0754. Min Act: -0.1700

Data Index: 8632426 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 2.0754. Min Range: -2.0754

Max Act: 2.0401. Min Act: -0.1700

Data Index: 2369783 (Open Web Text)

Max Activating Token Index: 561

Text #2

Max Range: 2.0754. Min Range: -2.0754

Max Act: 2.0194. Min Act: -0.1700

Data Index: 8184586 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 2.0754. Min Range: -2.0754

Max Act: 2.0212. Min Act: -0.1700

Data Index: 1007091 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 2.0754. Min Range: -2.0754

Max Act: 2.0019. Min Act: -0.1700

Data Index: 617428 (Open Web Text)

Max Activating Token Index: 555

Text #5

Max Range: 2.0754. Min Range: -2.0754

Max Act: 1.9999. Min Act: -0.1700

Data Index: 4855582 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 2.0754. Min Range: -2.0754

Max Act: 2.0145. Min Act: -0.1700

Data Index: 8212843 (Open Web Text)

Max Activating Token Index: 443

Text #7

Max Range: 2.0754. Min Range: -2.0754

Max Act: 2.0078. Min Act: -0.1700

Data Index: 3675969 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 2.0754. Min Range: -2.0754

Max Act: 1.9899. Min Act: -0.1700

Data Index: 5532812 (Open Web Text)

Max Activating Token Index: 162

Text #9

Max Range: 2.0754. Min Range: -2.0754

Max Act: 1.9905. Min Act: -0.1700

Data Index: 2791018 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 2.0754. Min Range: -2.0754

Max Act: 1.9771. Min Act: -0.1700

Data Index: 2826428 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 2.0754. Min Range: -2.0754

Max Act: 1.9804. Min Act: -0.1700

Data Index: 6931926 (Open Web Text)

Max Activating Token Index: 19

Text #12

Max Range: 2.0754. Min Range: -2.0754

Max Act: 1.9889. Min Act: -0.1700

Data Index: 7904283 (Open Web Text)

Max Activating Token Index: 24

Text #13

Max Range: 2.0754. Min Range: -2.0754

Max Act: 1.9675. Min Act: -0.1700

Data Index: 2125512 (Open Web Text)

Max Activating Token Index: 438

Text #14

Max Range: 2.0754. Min Range: -2.0754

Max Act: 1.9626. Min Act: -0.1700

Data Index: 8635785 (Open Web Text)

Max Activating Token Index: 917

Text #15

Max Range: 2.0754. Min Range: -2.0754

Max Act: 1.9597. Min Act: -0.1700

Data Index: 7968996 (Open Web Text)

Max Activating Token Index: 632

Text #16

Max Range: 2.0754. Min Range: -2.0754

Max Act: 1.9694. Min Act: -0.1700

Data Index: 4884855 (Open Web Text)

Max Activating Token Index: 687

Text #17

Max Range: 2.0754. Min Range: -2.0754

Max Act: 1.9733. Min Act: -0.1700

Data Index: 3119428 (Open Web Text)

Max Activating Token Index: 920

Text #18

Max Range: 2.0754. Min Range: -2.0754

Max Act: 1.9661. Min Act: -0.1700

Data Index: 479898 (Open Web Text)

Max Activating Token Index: 522

Text #19

Max Range: 2.0754. Min Range: -2.0754

Max Act: 1.9559. Min Act: -0.1700

Data Index: 3558880 (Open Web Text)

Max Activating Token Index: 5