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

Dataset: Open Web Text

Neuron 1893 in Layer 2

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: 5.7454. Min Range: -5.7454

Max Act: 5.7454. Min Act: -0.1700

Data Index: 5472710 (Open Web Text)

Max Activating Token Index: 31

Text #1

Max Range: 5.7454. Min Range: -5.7454

Max Act: 5.5328. Min Act: -0.1700

Data Index: 3996055 (Open Web Text)

Max Activating Token Index: 99

Text #2

Max Range: 5.7454. Min Range: -5.7454

Max Act: 5.4690. Min Act: -0.1700

Data Index: 8788466 (Open Web Text)

Max Activating Token Index: 329

Text #3

Max Range: 5.7454. Min Range: -5.7454

Max Act: 5.4407. Min Act: -0.1700

Data Index: 4615568 (Open Web Text)

Max Activating Token Index: 54

Text #4

Max Range: 5.7454. Min Range: -5.7454

Max Act: 5.4293. Min Act: -0.1700

Data Index: 556481 (Open Web Text)

Max Activating Token Index: 17

Text #5

Max Range: 5.7454. Min Range: -5.7454

Max Act: 5.4066. Min Act: -0.1700

Data Index: 2700031 (Open Web Text)

Max Activating Token Index: 49

Text #6

Max Range: 5.7454. Min Range: -5.7454

Max Act: 5.4235. Min Act: -0.1700

Data Index: 2149278 (Open Web Text)

Max Activating Token Index: 66

Text #7

Max Range: 5.7454. Min Range: -5.7454

Max Act: 5.3861. Min Act: -0.1700

Data Index: 5351704 (Open Web Text)

Max Activating Token Index: 54

Text #8

Max Range: 5.7454. Min Range: -5.7454

Max Act: 5.3124. Min Act: -0.1700

Data Index: 4105282 (Open Web Text)

Max Activating Token Index: 22

Text #9

Max Range: 5.7454. Min Range: -5.7454

Max Act: 5.3419. Min Act: -0.1700

Data Index: 5132511 (Open Web Text)

Max Activating Token Index: 392

Text #10

Max Range: 5.7454. Min Range: -5.7454

Max Act: 5.2840. Min Act: -0.1700

Data Index: 7826822 (Open Web Text)

Max Activating Token Index: 114

Text #11

Max Range: 5.7454. Min Range: -5.7454

Max Act: 5.2191. Min Act: -0.1700

Data Index: 3699166 (Open Web Text)

Max Activating Token Index: 819

Text #12

Max Range: 5.7454. Min Range: -5.7454

Max Act: 5.2379. Min Act: -0.1700

Data Index: 2484460 (Open Web Text)

Max Activating Token Index: 766

Text #13

Max Range: 5.7454. Min Range: -5.7454

Max Act: 5.2149. Min Act: -0.1700

Data Index: 6442546 (Open Web Text)

Max Activating Token Index: 253

Text #14

Max Range: 5.7454. Min Range: -5.7454

Max Act: 5.2315. Min Act: -0.1700

Data Index: 4396724 (Open Web Text)

Max Activating Token Index: 785

Text #15

Max Range: 5.7454. Min Range: -5.7454

Max Act: 5.1924. Min Act: -0.1699

Data Index: 5444388 (Open Web Text)

Max Activating Token Index: 19

Text #16

Max Range: 5.7454. Min Range: -5.7454

Max Act: 5.2256. Min Act: -0.1700

Data Index: 4365212 (Open Web Text)

Max Activating Token Index: 1002

Text #17

Max Range: 5.7454. Min Range: -5.7454

Max Act: 5.2047. Min Act: -0.1700

Data Index: 3245402 (Open Web Text)

Max Activating Token Index: 891

Text #18

Max Range: 5.7454. Min Range: -5.7454

Max Act: 5.1809. Min Act: -0.1698

Data Index: 1763602 (Open Web Text)

Max Activating Token Index: 49

Text #19

Max Range: 5.7454. Min Range: -5.7454

Max Act: 5.1856. Min Act: -0.1700

Data Index: 1215985 (Open Web Text)

Max Activating Token Index: 45