Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1237 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1211. Min Range: -8.1211
Max Act: 8.1211. Min Act: -0.1700
Data Index: 3550000 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1211. Min Range: -8.1211
Max Act: 8.0586. Min Act: -0.1700
Data Index: 8282959 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1211. Min Range: -8.1211
Max Act: 7.9961. Min Act: -0.1700
Data Index: 5202042 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1211. Min Range: -8.1211
Max Act: 8.0274. Min Act: -0.1700
Data Index: 5493545 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1211. Min Range: -8.1211
Max Act: 7.9649. Min Act: -0.1700
Data Index: 5193911 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1211. Min Range: -8.1211
Max Act: 7.9024. Min Act: -0.1700
Data Index: 854010 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1211. Min Range: -8.1211
Max Act: 7.8086. Min Act: -0.1700
Data Index: 129411 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1211. Min Range: -8.1211
Max Act: 7.7774. Min Act: -0.1700
Data Index: 4284257 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1211. Min Range: -8.1211
Max Act: 7.7461. Min Act: -0.1700
Data Index: 66719 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1211. Min Range: -8.1211
Max Act: 7.7149. Min Act: -0.1700
Data Index: 4094005 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1211. Min Range: -8.1211
Max Act: 7.6524. Min Act: -0.1700
Data Index: 3535100 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1211. Min Range: -8.1211
Max Act: 7.6211. Min Act: -0.1700
Data Index: 3760346 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1211. Min Range: -8.1211
Max Act: 7.6524. Min Act: -0.1700
Data Index: 2841461 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1211. Min Range: -8.1211
Max Act: 7.6524. Min Act: -0.1700
Data Index: 3070652 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1211. Min Range: -8.1211
Max Act: 7.6211. Min Act: -0.1700
Data Index: 6076028 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1211. Min Range: -8.1211
Max Act: 7.5899. Min Act: -0.1700
Data Index: 4991662 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1211. Min Range: -8.1211
Max Act: 7.5586. Min Act: -0.1700
Data Index: 6991817 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1211. Min Range: -8.1211
Max Act: 7.5899. Min Act: -0.1700
Data Index: 314764 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1211. Min Range: -8.1211
Max Act: 7.5899. Min Act: -0.1700
Data Index: 6296389 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1211. Min Range: -8.1211
Max Act: 7.5586. Min Act: -0.1700
Data Index: 6597988 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19