Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2849 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0753. Min Range: -10.0753
Max Act: 10.0753. Min Act: -0.1700
Data Index: 3528967 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0753. Min Range: -10.0753
Max Act: 9.5128. Min Act: -0.1700
Data Index: 7831729 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0753. Min Range: -10.0753
Max Act: 9.3253. Min Act: -0.1700
Data Index: 6450110 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0753. Min Range: -10.0753
Max Act: 9.2628. Min Act: -0.1700
Data Index: 3135274 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0753. Min Range: -10.0753
Max Act: 9.0753. Min Act: -0.1700
Data Index: 300224 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0753. Min Range: -10.0753
Max Act: 8.8253. Min Act: -0.1700
Data Index: 7432289 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0753. Min Range: -10.0753
Max Act: 8.8253. Min Act: -0.1700
Data Index: 6450109 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0753. Min Range: -10.0753
Max Act: 8.7628. Min Act: -0.1700
Data Index: 3555937 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0753. Min Range: -10.0753
Max Act: 8.7628. Min Act: -0.1700
Data Index: 42247 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0753. Min Range: -10.0753
Max Act: 8.7003. Min Act: -0.1700
Data Index: 8236190 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0753. Min Range: -10.0753
Max Act: 8.6378. Min Act: -0.1700
Data Index: 5041436 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0753. Min Range: -10.0753
Max Act: 8.6378. Min Act: -0.1700
Data Index: 5874709 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0753. Min Range: -10.0753
Max Act: 8.6378. Min Act: -0.1700
Data Index: 6450108 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0753. Min Range: -10.0753
Max Act: 8.5753. Min Act: -0.1700
Data Index: 3623566 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0753. Min Range: -10.0753
Max Act: 8.6378. Min Act: -0.1700
Data Index: 5799252 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0753. Min Range: -10.0753
Max Act: 8.5128. Min Act: -0.1700
Data Index: 1789141 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0753. Min Range: -10.0753
Max Act: 8.5128. Min Act: -0.1700
Data Index: 3528968 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0753. Min Range: -10.0753
Max Act: 8.4503. Min Act: -0.1700
Data Index: 5167395 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0753. Min Range: -10.0753
Max Act: 8.4503. Min Act: -0.1700
Data Index: 68977 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0753. Min Range: -10.0753
Max Act: 8.3878. Min Act: -0.1700
Data Index: 5516538 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #19