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

Dataset: Open Web Text

Neuron 2713 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: 4.9134. Min Range: -4.9134

Max Act: 4.9134. Min Act: -0.1700

Data Index: 349530 (Open Web Text)

Max Activating Token Index: 829

Text #1

Max Range: 4.9134. Min Range: -4.9134

Max Act: 4.8719. Min Act: -0.1700

Data Index: 3864891 (Open Web Text)

Max Activating Token Index: 531

Text #2

Max Range: 4.9134. Min Range: -4.9134

Max Act: 4.8567. Min Act: -0.1700

Data Index: 2155164 (Open Web Text)

Max Activating Token Index: 126

Text #3

Max Range: 4.9134. Min Range: -4.9134

Max Act: 4.7672. Min Act: -0.1700

Data Index: 8337793 (Open Web Text)

Max Activating Token Index: 856

Text #4

Max Range: 4.9134. Min Range: -4.9134

Max Act: 4.7483. Min Act: -0.1700

Data Index: 4941413 (Open Web Text)

Max Activating Token Index: 694

Text #5

Max Range: 4.9134. Min Range: -4.9134

Max Act: 4.7783. Min Act: -0.1700

Data Index: 5882011 (Open Web Text)

Max Activating Token Index: 949

Text #6

Max Range: 4.9134. Min Range: -4.9134

Max Act: 4.7519. Min Act: -0.1700

Data Index: 2651427 (Open Web Text)

Max Activating Token Index: 523

Text #7

Max Range: 4.9134. Min Range: -4.9134

Max Act: 4.9077. Min Act: -0.1700

Data Index: 8729648 (Open Web Text)

Max Activating Token Index: 927

Text #8

Max Range: 4.9134. Min Range: -4.9134

Max Act: 4.6627. Min Act: -0.1700

Data Index: 3624488 (Open Web Text)

Max Activating Token Index: 493

Text #9

Max Range: 4.9134. Min Range: -4.9134

Max Act: 4.8027. Min Act: -0.1700

Data Index: 8389584 (Open Web Text)

Max Activating Token Index: 925

Text #10

Max Range: 4.9134. Min Range: -4.9134

Max Act: 4.7964. Min Act: -0.1700

Data Index: 3227009 (Open Web Text)

Max Activating Token Index: 740

Text #11

Max Range: 4.9134. Min Range: -4.9134

Max Act: 4.7145. Min Act: -0.1700

Data Index: 8247064 (Open Web Text)

Max Activating Token Index: 871

Text #12

Max Range: 4.9134. Min Range: -4.9134

Max Act: 4.7264. Min Act: -0.1700

Data Index: 945882 (Open Web Text)

Max Activating Token Index: 898

Text #13

Max Range: 4.9134. Min Range: -4.9134

Max Act: 4.7116. Min Act: -0.1700

Data Index: 3279246 (Open Web Text)

Max Activating Token Index: 543

Text #14

Max Range: 4.9134. Min Range: -4.9134

Max Act: 4.7165. Min Act: -0.1700

Data Index: 4625851 (Open Web Text)

Max Activating Token Index: 612

Text #15

Max Range: 4.9134. Min Range: -4.9134

Max Act: 4.7373. Min Act: -0.1700

Data Index: 5036660 (Open Web Text)

Max Activating Token Index: 341

Text #16

Max Range: 4.9134. Min Range: -4.9134

Max Act: 4.6383. Min Act: -0.1700

Data Index: 7571143 (Open Web Text)

Max Activating Token Index: 836

Text #17

Max Range: 4.9134. Min Range: -4.9134

Max Act: 4.7747. Min Act: -0.1700

Data Index: 7401896 (Open Web Text)

Max Activating Token Index: 286

Text #18

Max Range: 4.9134. Min Range: -4.9134

Max Act: 4.7578. Min Act: -0.1700

Data Index: 5459457 (Open Web Text)

Max Activating Token Index: 434

Text #19

Max Range: 4.9134. Min Range: -4.9134

Max Act: 4.7710. Min Act: -0.1700

Data Index: 925505 (Open Web Text)

Max Activating Token Index: 471