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

Dataset: Open Web Text

Neuron 2655 in Layer 1

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: 1.8035. Min Range: -1.8035

Max Act: 1.8035. Min Act: -0.1700

Data Index: 7415469 (Open Web Text)

Max Activating Token Index: 57

Text #1

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.7419. Min Act: -0.1700

Data Index: 695467 (Open Web Text)

Max Activating Token Index: 191

Text #2

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.7337. Min Act: -0.1700

Data Index: 3528929 (Open Web Text)

Max Activating Token Index: 638

Text #3

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.7293. Min Act: -0.1700

Data Index: 4430997 (Open Web Text)

Max Activating Token Index: 975

Text #4

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.7134. Min Act: -0.1700

Data Index: 4566734 (Open Web Text)

Max Activating Token Index: 754

Text #5

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.7064. Min Act: -0.1700

Data Index: 6737046 (Open Web Text)

Max Activating Token Index: 484

Text #6

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.7072. Min Act: -0.1700

Data Index: 7948808 (Open Web Text)

Max Activating Token Index: 378

Text #7

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.6979. Min Act: -0.1700

Data Index: 8337980 (Open Web Text)

Max Activating Token Index: 709

Text #8

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.6945. Min Act: -0.1700

Data Index: 4281929 (Open Web Text)

Max Activating Token Index: 661

Text #9

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.6958. Min Act: -0.1700

Data Index: 7906148 (Open Web Text)

Max Activating Token Index: 993

Text #10

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.6880. Min Act: -0.1700

Data Index: 3935439 (Open Web Text)

Max Activating Token Index: 723

Text #11

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.6858. Min Act: -0.1700

Data Index: 158932 (Open Web Text)

Max Activating Token Index: 564

Text #12

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.6934. Min Act: -0.1700

Data Index: 5531576 (Open Web Text)

Max Activating Token Index: 409

Text #13

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.6935. Min Act: -0.1700

Data Index: 7233158 (Open Web Text)

Max Activating Token Index: 400

Text #14

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.6867. Min Act: -0.1700

Data Index: 5921457 (Open Web Text)

Max Activating Token Index: 284

Text #15

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.6875. Min Act: -0.1700

Data Index: 7228858 (Open Web Text)

Max Activating Token Index: 58

Text #16

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.6789. Min Act: -0.1700

Data Index: 70513 (Open Web Text)

Max Activating Token Index: 562

Text #17

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.6877. Min Act: -0.1700

Data Index: 2631620 (Open Web Text)

Max Activating Token Index: 272

Text #18

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.6825. Min Act: -0.1700

Data Index: 2808004 (Open Web Text)

Max Activating Token Index: 42

Text #19

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.6820. Min Act: -0.1700

Data Index: 2163010 (Open Web Text)

Max Activating Token Index: 358