Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3282 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7245. Min Range: -6.7245
Max Act: 6.7245. Min Act: -0.1700
Data Index: 3559426 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7245. Min Range: -6.7245
Max Act: 6.7245. Min Act: -0.1700
Data Index: 5671166 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7245. Min Range: -6.7245
Max Act: 6.6307. Min Act: -0.1700
Data Index: 5340166 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7245. Min Range: -6.7245
Max Act: 6.5995. Min Act: -0.1700
Data Index: 3930393 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7245. Min Range: -6.7245
Max Act: 6.5995. Min Act: -0.1700
Data Index: 4657029 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7245. Min Range: -6.7245
Max Act: 6.5370. Min Act: -0.1700
Data Index: 1190626 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7245. Min Range: -6.7245
Max Act: 6.5057. Min Act: -0.1700
Data Index: 269443 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7245. Min Range: -6.7245
Max Act: 6.4432. Min Act: -0.1700
Data Index: 2287208 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7245. Min Range: -6.7245
Max Act: 6.4432. Min Act: -0.1700
Data Index: 2727176 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7245. Min Range: -6.7245
Max Act: 6.4432. Min Act: -0.1700
Data Index: 4603847 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7245. Min Range: -6.7245
Max Act: 6.4432. Min Act: -0.1700
Data Index: 5542737 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7245. Min Range: -6.7245
Max Act: 6.3495. Min Act: -0.1700
Data Index: 3815449 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7245. Min Range: -6.7245
Max Act: 6.3495. Min Act: -0.1700
Data Index: 6511666 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7245. Min Range: -6.7245
Max Act: 6.3182. Min Act: -0.1700
Data Index: 5134440 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7245. Min Range: -6.7245
Max Act: 6.3182. Min Act: -0.1700
Data Index: 2428856 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7245. Min Range: -6.7245
Max Act: 6.3182. Min Act: -0.1700
Data Index: 789819 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7245. Min Range: -6.7245
Max Act: 6.2557. Min Act: -0.1700
Data Index: 1411174 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7245. Min Range: -6.7245
Max Act: 6.3182. Min Act: -0.1700
Data Index: 2013193 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7245. Min Range: -6.7245
Max Act: 6.2557. Min Act: -0.1700
Data Index: 3181233 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7245. Min Range: -6.7245
Max Act: 6.2870. Min Act: -0.1700
Data Index: 2369624 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #19