Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3012 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8061. Min Range: -2.8061
Max Act: 2.8061. Min Act: -0.1700
Data Index: 6591606 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8061. Min Range: -2.8061
Max Act: 2.7742. Min Act: -0.1700
Data Index: 5997487 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8061. Min Range: -2.8061
Max Act: 2.7104. Min Act: -0.1700
Data Index: 3652797 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8061. Min Range: -2.8061
Max Act: 2.7264. Min Act: -0.1700
Data Index: 8565581 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8061. Min Range: -2.8061
Max Act: 2.6944. Min Act: -0.1700
Data Index: 5227268 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8061. Min Range: -2.8061
Max Act: 2.7104. Min Act: -0.1700
Data Index: 4531559 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8061. Min Range: -2.8061
Max Act: 2.6623. Min Act: -0.1700
Data Index: 6111589 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8061. Min Range: -2.8061
Max Act: 2.6784. Min Act: -0.1700
Data Index: 3196044 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8061. Min Range: -2.8061
Max Act: 2.6463. Min Act: -0.1700
Data Index: 7298564 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8061. Min Range: -2.8061
Max Act: 2.5981. Min Act: -0.1700
Data Index: 488812 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8061. Min Range: -2.8061
Max Act: 2.6623. Min Act: -0.1700
Data Index: 1120501 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8061. Min Range: -2.8061
Max Act: 2.6302. Min Act: -0.1700
Data Index: 172829 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8061. Min Range: -2.8061
Max Act: 2.6302. Min Act: -0.1700
Data Index: 3293582 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8061. Min Range: -2.8061
Max Act: 2.6302. Min Act: -0.1700
Data Index: 4976822 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8061. Min Range: -2.8061
Max Act: 2.6463. Min Act: -0.1700
Data Index: 5516004 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8061. Min Range: -2.8061
Max Act: 2.6141. Min Act: -0.1700
Data Index: 4553496 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8061. Min Range: -2.8061
Max Act: 2.5981. Min Act: -0.1700
Data Index: 8328168 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8061. Min Range: -2.8061
Max Act: 2.6302. Min Act: -0.1700
Data Index: 2798547 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8061. Min Range: -2.8061
Max Act: 2.5820. Min Act: -0.1700
Data Index: 2350360 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8061. Min Range: -2.8061
Max Act: 2.6302. Min Act: -0.1700
Data Index: 2782894 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #19