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

Dataset: Open Web Text

Neuron 1779 in Layer 0

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: 2.0267. Min Range: -2.0267

Max Act: 2.0252. Min Act: -0.1700

Data Index: 4646667 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 2.0267. Min Range: -2.0267

Max Act: 2.0154. Min Act: -0.1700

Data Index: 7479296 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 2.0267. Min Range: -2.0267

Max Act: 2.0267. Min Act: -0.1700

Data Index: 7838191 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 2.0267. Min Range: -2.0267

Max Act: 2.0176. Min Act: -0.1700

Data Index: 8809639 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 2.0267. Min Range: -2.0267

Max Act: 2.0262. Min Act: -0.1700

Data Index: 3513275 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 2.0267. Min Range: -2.0267

Max Act: 2.0199. Min Act: -0.1700

Data Index: 1592243 (Open Web Text)

Max Activating Token Index: 10

Text #6

Max Range: 2.0267. Min Range: -2.0267

Max Act: 2.0146. Min Act: -0.1700

Data Index: 386646 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 2.0267. Min Range: -2.0267

Max Act: 2.0006. Min Act: -0.1700

Data Index: 5348363 (Open Web Text)

Max Activating Token Index: 10

Text #8

Max Range: 2.0267. Min Range: -2.0267

Max Act: 2.0083. Min Act: -0.1700

Data Index: 6220416 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 2.0267. Min Range: -2.0267

Max Act: 2.0131. Min Act: -0.1700

Data Index: 3505033 (Open Web Text)

Max Activating Token Index: 9

Text #10

Max Range: 2.0267. Min Range: -2.0267

Max Act: 1.9997. Min Act: -0.1700

Data Index: 557193 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 2.0267. Min Range: -2.0267

Max Act: 2.0071. Min Act: -0.1700

Data Index: 2444382 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 2.0267. Min Range: -2.0267

Max Act: 2.0040. Min Act: -0.1700

Data Index: 762194 (Open Web Text)

Max Activating Token Index: 14

Text #13

Max Range: 2.0267. Min Range: -2.0267

Max Act: 1.9932. Min Act: -0.1700

Data Index: 4393663 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 2.0267. Min Range: -2.0267

Max Act: 1.9794. Min Act: -0.1700

Data Index: 171037 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 2.0267. Min Range: -2.0267

Max Act: 1.9867. Min Act: -0.1700

Data Index: 2282265 (Open Web Text)

Max Activating Token Index: 11

Text #16

Max Range: 2.0267. Min Range: -2.0267

Max Act: 1.9870. Min Act: -0.1700

Data Index: 1987721 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 2.0267. Min Range: -2.0267

Max Act: 1.9863. Min Act: -0.1700

Data Index: 3941988 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 2.0267. Min Range: -2.0267

Max Act: 1.9928. Min Act: -0.1700

Data Index: 3894823 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 2.0267. Min Range: -2.0267

Max Act: 1.9883. Min Act: -0.1700

Data Index: 3813835 (Open Web Text)

Max Activating Token Index: 11