Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2400 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9589. Min Range: -8.9589
Max Act: 8.9589. Min Act: -0.1700
Data Index: 5708500 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9589. Min Range: -8.9589
Max Act: 8.8339. Min Act: -0.1700
Data Index: 4753938 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9589. Min Range: -8.9589
Max Act: 8.8339. Min Act: -0.1700
Data Index: 313955 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9589. Min Range: -8.9589
Max Act: 8.7714. Min Act: -0.1700
Data Index: 1563067 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9589. Min Range: -8.9589
Max Act: 8.6464. Min Act: -0.1700
Data Index: 5910888 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9589. Min Range: -8.9589
Max Act: 8.5839. Min Act: -0.1700
Data Index: 1808682 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9589. Min Range: -8.9589
Max Act: 8.5839. Min Act: -0.1700
Data Index: 3141785 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9589. Min Range: -8.9589
Max Act: 8.5839. Min Act: -0.1700
Data Index: 6855916 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9589. Min Range: -8.9589
Max Act: 8.5839. Min Act: -0.1700
Data Index: 4002497 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9589. Min Range: -8.9589
Max Act: 8.5214. Min Act: -0.1700
Data Index: 520095 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9589. Min Range: -8.9589
Max Act: 8.4589. Min Act: -0.1700
Data Index: 8503275 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9589. Min Range: -8.9589
Max Act: 8.3339. Min Act: -0.1700
Data Index: 897298 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9589. Min Range: -8.9589
Max Act: 8.3964. Min Act: -0.1700
Data Index: 8408189 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9589. Min Range: -8.9589
Max Act: 8.3964. Min Act: -0.1700
Data Index: 8807086 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9589. Min Range: -8.9589
Max Act: 8.3339. Min Act: -0.1700
Data Index: 4656829 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9589. Min Range: -8.9589
Max Act: 8.3339. Min Act: -0.1700
Data Index: 8351229 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9589. Min Range: -8.9589
Max Act: 8.3339. Min Act: -0.1700
Data Index: 8060047 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9589. Min Range: -8.9589
Max Act: 8.2714. Min Act: -0.1700
Data Index: 792055 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9589. Min Range: -8.9589
Max Act: 8.2714. Min Act: -0.1700
Data Index: 6678946 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9589. Min Range: -8.9589
Max Act: 8.2714. Min Act: -0.1700
Data Index: 8596701 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #19