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

Dataset: Open Web Text

Neuron 171 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: 4.7902. Min Range: -4.7902

Max Act: 4.7902. Min Act: -0.1700

Data Index: 4612233 (Open Web Text)

Max Activating Token Index: 910

Text #1

Max Range: 4.7902. Min Range: -4.7902

Max Act: 4.7753. Min Act: -0.1700

Data Index: 7202121 (Open Web Text)

Max Activating Token Index: 490

Text #2

Max Range: 4.7902. Min Range: -4.7902

Max Act: 4.7672. Min Act: -0.1700

Data Index: 2801206 (Open Web Text)

Max Activating Token Index: 577

Text #3

Max Range: 4.7902. Min Range: -4.7902

Max Act: 4.7502. Min Act: -0.1700

Data Index: 2900319 (Open Web Text)

Max Activating Token Index: 584

Text #4

Max Range: 4.7902. Min Range: -4.7902

Max Act: 4.6455. Min Act: -0.1700

Data Index: 7825485 (Open Web Text)

Max Activating Token Index: 970

Text #5

Max Range: 4.7902. Min Range: -4.7902

Max Act: 4.6982. Min Act: -0.1700

Data Index: 4016836 (Open Web Text)

Max Activating Token Index: 371

Text #6

Max Range: 4.7902. Min Range: -4.7902

Max Act: 4.6802. Min Act: -0.1700

Data Index: 4657933 (Open Web Text)

Max Activating Token Index: 79

Text #7

Max Range: 4.7902. Min Range: -4.7902

Max Act: 4.6169. Min Act: -0.1700

Data Index: 7817796 (Open Web Text)

Max Activating Token Index: 180

Text #8

Max Range: 4.7902. Min Range: -4.7902

Max Act: 4.6219. Min Act: -0.1700

Data Index: 1589713 (Open Web Text)

Max Activating Token Index: 277

Text #9

Max Range: 4.7902. Min Range: -4.7902

Max Act: 4.6111. Min Act: -0.1700

Data Index: 8311534 (Open Web Text)

Max Activating Token Index: 466

Text #10

Max Range: 4.7902. Min Range: -4.7902

Max Act: 4.6051. Min Act: -0.1700

Data Index: 5598650 (Open Web Text)

Max Activating Token Index: 195

Text #11

Max Range: 4.7902. Min Range: -4.7902

Max Act: 4.6080. Min Act: -0.1700

Data Index: 7156865 (Open Web Text)

Max Activating Token Index: 21

Text #12

Max Range: 4.7902. Min Range: -4.7902

Max Act: 4.5622. Min Act: -0.1700

Data Index: 4629939 (Open Web Text)

Max Activating Token Index: 552

Text #13

Max Range: 4.7902. Min Range: -4.7902

Max Act: 4.5685. Min Act: -0.1700

Data Index: 7602305 (Open Web Text)

Max Activating Token Index: 20

Text #14

Max Range: 4.7902. Min Range: -4.7902

Max Act: 4.5696. Min Act: -0.1700

Data Index: 3064505 (Open Web Text)

Max Activating Token Index: 731

Text #15

Max Range: 4.7902. Min Range: -4.7902

Max Act: 4.5803. Min Act: -0.1700

Data Index: 3293012 (Open Web Text)

Max Activating Token Index: 78

Text #16

Max Range: 4.7902. Min Range: -4.7902

Max Act: 4.5605. Min Act: -0.1700

Data Index: 7500340 (Open Web Text)

Max Activating Token Index: 640

Text #17

Max Range: 4.7902. Min Range: -4.7902

Max Act: 4.5434. Min Act: -0.1700

Data Index: 1738072 (Open Web Text)

Max Activating Token Index: 116

Text #18

Max Range: 4.7902. Min Range: -4.7902

Max Act: 4.5694. Min Act: -0.1700

Data Index: 6344005 (Open Web Text)

Max Activating Token Index: 833

Text #19

Max Range: 4.7902. Min Range: -4.7902

Max Act: 4.5439. Min Act: -0.1700

Data Index: 7644515 (Open Web Text)

Max Activating Token Index: 583