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

Dataset: Open Web Text

Neuron 2471 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: 2.6896. Min Range: -2.6896

Max Act: 2.6771. Min Act: -0.1700

Data Index: 8598226 (Open Web Text)

Max Activating Token Index: 677

Text #1

Max Range: 2.6896. Min Range: -2.6896

Max Act: 2.6896. Min Act: -0.1700

Data Index: 7880141 (Open Web Text)

Max Activating Token Index: 895

Text #2

Max Range: 2.6896. Min Range: -2.6896

Max Act: 2.6622. Min Act: -0.1700

Data Index: 8016101 (Open Web Text)

Max Activating Token Index: 436

Text #3

Max Range: 2.6896. Min Range: -2.6896

Max Act: 2.6376. Min Act: -0.1700

Data Index: 2901066 (Open Web Text)

Max Activating Token Index: 1008

Text #4

Max Range: 2.6896. Min Range: -2.6896

Max Act: 2.6369. Min Act: -0.1700

Data Index: 8644855 (Open Web Text)

Max Activating Token Index: 994

Text #5

Max Range: 2.6896. Min Range: -2.6896

Max Act: 2.6197. Min Act: -0.1700

Data Index: 18609 (Open Web Text)

Max Activating Token Index: 409

Text #6

Max Range: 2.6896. Min Range: -2.6896

Max Act: 2.6060. Min Act: -0.1700

Data Index: 675582 (Open Web Text)

Max Activating Token Index: 317

Text #7

Max Range: 2.6896. Min Range: -2.6896

Max Act: 2.6107. Min Act: -0.1700

Data Index: 7817792 (Open Web Text)

Max Activating Token Index: 495

Text #8

Max Range: 2.6896. Min Range: -2.6896

Max Act: 2.6116. Min Act: -0.1700

Data Index: 8102053 (Open Web Text)

Max Activating Token Index: 431

Text #9

Max Range: 2.6896. Min Range: -2.6896

Max Act: 2.6013. Min Act: -0.1700

Data Index: 21752 (Open Web Text)

Max Activating Token Index: 477

Text #10

Max Range: 2.6896. Min Range: -2.6896

Max Act: 2.5911. Min Act: -0.1700

Data Index: 2736994 (Open Web Text)

Max Activating Token Index: 233

Text #11

Max Range: 2.6896. Min Range: -2.6896

Max Act: 2.5830. Min Act: -0.1700

Data Index: 1663967 (Open Web Text)

Max Activating Token Index: 747

Text #12

Max Range: 2.6896. Min Range: -2.6896

Max Act: 2.5999. Min Act: -0.1700

Data Index: 4752866 (Open Web Text)

Max Activating Token Index: 100

Text #13

Max Range: 2.6896. Min Range: -2.6896

Max Act: 2.5721. Min Act: -0.1700

Data Index: 4214584 (Open Web Text)

Max Activating Token Index: 410

Text #14

Max Range: 2.6896. Min Range: -2.6896

Max Act: 2.6025. Min Act: -0.1700

Data Index: 3294033 (Open Web Text)

Max Activating Token Index: 295

Text #15

Max Range: 2.6896. Min Range: -2.6896

Max Act: 2.5765. Min Act: -0.1700

Data Index: 1786411 (Open Web Text)

Max Activating Token Index: 794

Text #16

Max Range: 2.6896. Min Range: -2.6896

Max Act: 2.5707. Min Act: -0.1700

Data Index: 4268741 (Open Web Text)

Max Activating Token Index: 395

Text #17

Max Range: 2.6896. Min Range: -2.6896

Max Act: 2.5665. Min Act: -0.1700

Data Index: 4227448 (Open Web Text)

Max Activating Token Index: 486

Text #18

Max Range: 2.6896. Min Range: -2.6896

Max Act: 2.5682. Min Act: -0.1700

Data Index: 7848793 (Open Web Text)

Max Activating Token Index: 245

Text #19

Max Range: 2.6896. Min Range: -2.6896

Max Act: 2.5724. Min Act: -0.1700

Data Index: 2982478 (Open Web Text)

Max Activating Token Index: 438