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

Dataset: Open Web Text

Neuron 2594 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: 6.5392. Min Range: -6.5392

Max Act: 6.5392. Min Act: -0.1700

Data Index: 7136933 (Open Web Text)

Max Activating Token Index: 299

Text #1

Max Range: 6.5392. Min Range: -6.5392

Max Act: 6.2766. Min Act: -0.1700

Data Index: 8076804 (Open Web Text)

Max Activating Token Index: 675

Text #2

Max Range: 6.5392. Min Range: -6.5392

Max Act: 6.1741. Min Act: -0.1700

Data Index: 276726 (Open Web Text)

Max Activating Token Index: 161

Text #3

Max Range: 6.5392. Min Range: -6.5392

Max Act: 6.1166. Min Act: -0.1700

Data Index: 2961979 (Open Web Text)

Max Activating Token Index: 164

Text #4

Max Range: 6.5392. Min Range: -6.5392

Max Act: 6.1043. Min Act: -0.1700

Data Index: 2177635 (Open Web Text)

Max Activating Token Index: 743

Text #5

Max Range: 6.5392. Min Range: -6.5392

Max Act: 6.0608. Min Act: -0.1700

Data Index: 8615259 (Open Web Text)

Max Activating Token Index: 311

Text #6

Max Range: 6.5392. Min Range: -6.5392

Max Act: 6.0541. Min Act: -0.1700

Data Index: 1808050 (Open Web Text)

Max Activating Token Index: 764

Text #7

Max Range: 6.5392. Min Range: -6.5392

Max Act: 6.0010. Min Act: -0.1700

Data Index: 3651953 (Open Web Text)

Max Activating Token Index: 828

Text #8

Max Range: 6.5392. Min Range: -6.5392

Max Act: 5.9940. Min Act: -0.1700

Data Index: 3054819 (Open Web Text)

Max Activating Token Index: 80

Text #9

Max Range: 6.5392. Min Range: -6.5392

Max Act: 5.9866. Min Act: -0.1700

Data Index: 1342057 (Open Web Text)

Max Activating Token Index: 289

Text #10

Max Range: 6.5392. Min Range: -6.5392

Max Act: 5.9896. Min Act: -0.1700

Data Index: 1978992 (Open Web Text)

Max Activating Token Index: 596

Text #11

Max Range: 6.5392. Min Range: -6.5392

Max Act: 5.9751. Min Act: -0.1700

Data Index: 5480635 (Open Web Text)

Max Activating Token Index: 333

Text #12

Max Range: 6.5392. Min Range: -6.5392

Max Act: 5.9412. Min Act: -0.1700

Data Index: 6599846 (Open Web Text)

Max Activating Token Index: 169

Text #13

Max Range: 6.5392. Min Range: -6.5392

Max Act: 5.9431. Min Act: -0.1700

Data Index: 7047911 (Open Web Text)

Max Activating Token Index: 894

Text #14

Max Range: 6.5392. Min Range: -6.5392

Max Act: 5.8707. Min Act: -0.1700

Data Index: 4455025 (Open Web Text)

Max Activating Token Index: 107

Text #15

Max Range: 6.5392. Min Range: -6.5392

Max Act: 5.9125. Min Act: -0.1700

Data Index: 6966696 (Open Web Text)

Max Activating Token Index: 658

Text #16

Max Range: 6.5392. Min Range: -6.5392

Max Act: 5.8754. Min Act: -0.1700

Data Index: 2422954 (Open Web Text)

Max Activating Token Index: 267

Text #17

Max Range: 6.5392. Min Range: -6.5392

Max Act: 5.8964. Min Act: -0.1700

Data Index: 7052333 (Open Web Text)

Max Activating Token Index: 736

Text #18

Max Range: 6.5392. Min Range: -6.5392

Max Act: 5.9015. Min Act: -0.1700

Data Index: 231593 (Open Web Text)

Max Activating Token Index: 361

Text #19

Max Range: 6.5392. Min Range: -6.5392

Max Act: 5.8829. Min Act: -0.1700

Data Index: 8033376 (Open Web Text)

Max Activating Token Index: 527