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

Dataset: Open Web Text

Neuron 352 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: 0.8540. Min Range: -0.8540

Max Act: 0.8540. Min Act: -0.1700

Data Index: 1183242 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.8315. Min Act: -0.1700

Data Index: 3104958 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.8267. Min Act: -0.1700

Data Index: 1801574 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.8296. Min Act: -0.1700

Data Index: 1942243 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.8331. Min Act: -0.1700

Data Index: 8343102 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.8267. Min Act: -0.1700

Data Index: 3942690 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.8245. Min Act: -0.1700

Data Index: 5134375 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.8267. Min Act: -0.1700

Data Index: 6387614 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.8124. Min Act: -0.1700

Data Index: 8752028 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.8108. Min Act: -0.1700

Data Index: 1295761 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.8152. Min Act: -0.1700

Data Index: 5642889 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.8155. Min Act: -0.1700

Data Index: 8173312 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.8123. Min Act: -0.1700

Data Index: 8002972 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.8138. Min Act: -0.1700

Data Index: 3766143 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.8080. Min Act: -0.1700

Data Index: 7391492 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.8103. Min Act: -0.1700

Data Index: 104301 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.7919. Min Act: -0.1700

Data Index: 3095946 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.8045. Min Act: -0.1698

Data Index: 2177705 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.7924. Min Act: -0.1700

Data Index: 5254951 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.8037. Min Act: -0.1700

Data Index: 259567 (Open Web Text)

Max Activating Token Index: 3