Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3109 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0191. Min Range: -6.0191
Max Act: 6.0191. Min Act: -0.1700
Data Index: 3691892 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0191. Min Range: -6.0191
Max Act: 5.9566. Min Act: -0.1700
Data Index: 2893041 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0191. Min Range: -6.0191
Max Act: 5.9254. Min Act: -0.1700
Data Index: 712060 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0191. Min Range: -6.0191
Max Act: 5.9254. Min Act: -0.1700
Data Index: 5639980 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0191. Min Range: -6.0191
Max Act: 5.8941. Min Act: -0.1700
Data Index: 2631689 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0191. Min Range: -6.0191
Max Act: 5.8316. Min Act: -0.1700
Data Index: 1023850 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0191. Min Range: -6.0191
Max Act: 5.8316. Min Act: -0.1700
Data Index: 3465502 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0191. Min Range: -6.0191
Max Act: 5.8316. Min Act: -0.1700
Data Index: 8092900 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0191. Min Range: -6.0191
Max Act: 5.8316. Min Act: -0.1700
Data Index: 5788594 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0191. Min Range: -6.0191
Max Act: 5.8004. Min Act: -0.1700
Data Index: 4033538 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0191. Min Range: -6.0191
Max Act: 5.8004. Min Act: -0.1699
Data Index: 8568553 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0191. Min Range: -6.0191
Max Act: 5.8004. Min Act: -0.1700
Data Index: 4552874 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0191. Min Range: -6.0191
Max Act: 5.8004. Min Act: -0.1700
Data Index: 584904 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0191. Min Range: -6.0191
Max Act: 5.7379. Min Act: -0.1700
Data Index: 920176 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0191. Min Range: -6.0191
Max Act: 5.7691. Min Act: -0.1700
Data Index: 1288066 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0191. Min Range: -6.0191
Max Act: 5.7691. Min Act: -0.1700
Data Index: 3124841 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0191. Min Range: -6.0191
Max Act: 5.7691. Min Act: -0.1700
Data Index: 2586303 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0191. Min Range: -6.0191
Max Act: 5.7691. Min Act: -0.1700
Data Index: 5956572 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0191. Min Range: -6.0191
Max Act: 5.7691. Min Act: -0.1698
Data Index: 6276501 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0191. Min Range: -6.0191
Max Act: 5.7379. Min Act: -0.1700
Data Index: 2403526 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19