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

Dataset: Open Web Text

Neuron 581 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: 2.6710. Min Range: -2.6710

Max Act: 2.6710. Min Act: -0.1700

Data Index: 731795 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 2.6710. Min Range: -2.6710

Max Act: 2.6544. Min Act: -0.1700

Data Index: 5200188 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 2.6710. Min Range: -2.6710

Max Act: 2.6471. Min Act: -0.1700

Data Index: 6008501 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 2.6710. Min Range: -2.6710

Max Act: 2.6384. Min Act: -0.1700

Data Index: 6241395 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 2.6710. Min Range: -2.6710

Max Act: 2.6179. Min Act: -0.1700

Data Index: 2840907 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 2.6710. Min Range: -2.6710

Max Act: 2.6258. Min Act: -0.1700

Data Index: 6278976 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 2.6710. Min Range: -2.6710

Max Act: 2.6298. Min Act: -0.1700

Data Index: 761497 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 2.6710. Min Range: -2.6710

Max Act: 2.6289. Min Act: -0.1700

Data Index: 239123 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 2.6710. Min Range: -2.6710

Max Act: 2.6311. Min Act: -0.1700

Data Index: 1278354 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 2.6710. Min Range: -2.6710

Max Act: 2.6240. Min Act: -0.1700

Data Index: 8362205 (Open Web Text)

Max Activating Token Index: 647

Text #10

Max Range: 2.6710. Min Range: -2.6710

Max Act: 2.6298. Min Act: -0.1700

Data Index: 6965079 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 2.6710. Min Range: -2.6710

Max Act: 2.6251. Min Act: -0.1700

Data Index: 6780825 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 2.6710. Min Range: -2.6710

Max Act: 2.6085. Min Act: -0.1700

Data Index: 5394952 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 2.6710. Min Range: -2.6710

Max Act: 2.6023. Min Act: -0.1700

Data Index: 5454320 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 2.6710. Min Range: -2.6710

Max Act: 2.6057. Min Act: -0.1700

Data Index: 5732876 (Open Web Text)

Max Activating Token Index: 14

Text #15

Max Range: 2.6710. Min Range: -2.6710

Max Act: 2.6067. Min Act: -0.1700

Data Index: 219476 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 2.6710. Min Range: -2.6710

Max Act: 2.6067. Min Act: -0.1700

Data Index: 1258261 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 2.6710. Min Range: -2.6710

Max Act: 2.6079. Min Act: -0.1700

Data Index: 6241952 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 2.6710. Min Range: -2.6710

Max Act: 2.6127. Min Act: -0.1700

Data Index: 6270698 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 2.6710. Min Range: -2.6710

Max Act: 2.6069. Min Act: -0.1700

Data Index: 2435827 (Open Web Text)

Max Activating Token Index: 3