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

Dataset: Open Web Text

Neuron 625 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: 4.8006. Min Range: -4.8006

Max Act: 4.8006. Min Act: -0.1700

Data Index: 8074894 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 4.8006. Min Range: -4.8006

Max Act: 4.6881. Min Act: -0.1700

Data Index: 8731156 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.8006. Min Range: -4.8006

Max Act: 4.7094. Min Act: -0.1700

Data Index: 753857 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 4.8006. Min Range: -4.8006

Max Act: 4.7049. Min Act: -0.1700

Data Index: 7204248 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 4.8006. Min Range: -4.8006

Max Act: 4.6834. Min Act: -0.1700

Data Index: 1858667 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 4.8006. Min Range: -4.8006

Max Act: 4.6554. Min Act: -0.1700

Data Index: 4513827 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 4.8006. Min Range: -4.8006

Max Act: 4.6296. Min Act: -0.1700

Data Index: 8366590 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 4.8006. Min Range: -4.8006

Max Act: 4.6539. Min Act: -0.1700

Data Index: 3754477 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 4.8006. Min Range: -4.8006

Max Act: 4.6476. Min Act: -0.1700

Data Index: 8060720 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 4.8006. Min Range: -4.8006

Max Act: 4.6302. Min Act: -0.1700

Data Index: 7431202 (Open Web Text)

Max Activating Token Index: 9

Text #10

Max Range: 4.8006. Min Range: -4.8006

Max Act: 4.6410. Min Act: -0.1700

Data Index: 2745252 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 4.8006. Min Range: -4.8006

Max Act: 4.6379. Min Act: -0.1700

Data Index: 2524269 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 4.8006. Min Range: -4.8006

Max Act: 4.6423. Min Act: -0.1700

Data Index: 5603766 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 4.8006. Min Range: -4.8006

Max Act: 4.6404. Min Act: -0.1700

Data Index: 4683045 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 4.8006. Min Range: -4.8006

Max Act: 4.6140. Min Act: -0.1700

Data Index: 5578952 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 4.8006. Min Range: -4.8006

Max Act: 4.6153. Min Act: -0.1700

Data Index: 7609625 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.8006. Min Range: -4.8006

Max Act: 4.6106. Min Act: -0.1700

Data Index: 7763325 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 4.8006. Min Range: -4.8006

Max Act: 4.6122. Min Act: -0.1700

Data Index: 5176317 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 4.8006. Min Range: -4.8006

Max Act: 4.6038. Min Act: -0.1700

Data Index: 872957 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 4.8006. Min Range: -4.8006

Max Act: 4.6120. Min Act: -0.1700

Data Index: 4300088 (Open Web Text)

Max Activating Token Index: 5