Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2245 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1746. Min Range: -6.1746
Max Act: 6.1746. Min Act: -0.1700
Data Index: 1381714 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1746. Min Range: -6.1746
Max Act: 6.1434. Min Act: -0.1700
Data Index: 2548496 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1746. Min Range: -6.1746
Max Act: 5.8934. Min Act: -0.1700
Data Index: 746855 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1746. Min Range: -6.1746
Max Act: 5.8934. Min Act: -0.1700
Data Index: 4056147 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1746. Min Range: -6.1746
Max Act: 5.8934. Min Act: -0.1700
Data Index: 2224859 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1746. Min Range: -6.1746
Max Act: 5.8309. Min Act: -0.1700
Data Index: 1193426 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1746. Min Range: -6.1746
Max Act: 5.8621. Min Act: -0.1700
Data Index: 2688951 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1746. Min Range: -6.1746
Max Act: 5.8309. Min Act: -0.1700
Data Index: 2578451 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1746. Min Range: -6.1746
Max Act: 5.7996. Min Act: -0.1700
Data Index: 3792575 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1746. Min Range: -6.1746
Max Act: 5.7684. Min Act: -0.1700
Data Index: 5320993 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1746. Min Range: -6.1746
Max Act: 5.7684. Min Act: -0.1700
Data Index: 73909 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1746. Min Range: -6.1746
Max Act: 5.7996. Min Act: -0.1700
Data Index: 8591593 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1746. Min Range: -6.1746
Max Act: 5.7684. Min Act: -0.1700
Data Index: 531695 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1746. Min Range: -6.1746
Max Act: 5.7684. Min Act: -0.1700
Data Index: 4834905 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1746. Min Range: -6.1746
Max Act: 5.7684. Min Act: -0.1700
Data Index: 1727810 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1746. Min Range: -6.1746
Max Act: 5.7371. Min Act: -0.1700
Data Index: 1049344 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1746. Min Range: -6.1746
Max Act: 5.7059. Min Act: -0.1700
Data Index: 5661852 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1746. Min Range: -6.1746
Max Act: 5.7059. Min Act: -0.1700
Data Index: 1393224 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1746. Min Range: -6.1746
Max Act: 5.7371. Min Act: -0.1700
Data Index: 7477219 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1746. Min Range: -6.1746
Max Act: 5.7059. Min Act: -0.1700
Data Index: 1580881 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19