Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3051 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0016. Min Range: -8.0016
Max Act: 8.0016. Min Act: -0.1700
Data Index: 8088071 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0016. Min Range: -8.0016
Max Act: 7.8766. Min Act: -0.1700
Data Index: 8426315 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0016. Min Range: -8.0016
Max Act: 7.8766. Min Act: -0.1700
Data Index: 1029787 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0016. Min Range: -8.0016
Max Act: 7.8141. Min Act: -0.1700
Data Index: 4989692 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0016. Min Range: -8.0016
Max Act: 7.7516. Min Act: -0.1700
Data Index: 2292919 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0016. Min Range: -8.0016
Max Act: 7.7516. Min Act: -0.1700
Data Index: 6408628 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0016. Min Range: -8.0016
Max Act: 7.7516. Min Act: -0.1700
Data Index: 4443783 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0016. Min Range: -8.0016
Max Act: 7.6891. Min Act: -0.1700
Data Index: 7066152 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0016. Min Range: -8.0016
Max Act: 7.7516. Min Act: -0.1700
Data Index: 719041 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0016. Min Range: -8.0016
Max Act: 7.6891. Min Act: -0.1700
Data Index: 4502464 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0016. Min Range: -8.0016
Max Act: 7.6891. Min Act: -0.1700
Data Index: 7694687 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0016. Min Range: -8.0016
Max Act: 7.6266. Min Act: -0.1700
Data Index: 8006927 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0016. Min Range: -8.0016
Max Act: 7.6266. Min Act: -0.1700
Data Index: 6291181 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0016. Min Range: -8.0016
Max Act: 7.6266. Min Act: -0.1700
Data Index: 3959553 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0016. Min Range: -8.0016
Max Act: 7.6266. Min Act: -0.1700
Data Index: 8478815 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0016. Min Range: -8.0016
Max Act: 7.6266. Min Act: -0.1700
Data Index: 2409978 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0016. Min Range: -8.0016
Max Act: 7.5641. Min Act: -0.1700
Data Index: 57563 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0016. Min Range: -8.0016
Max Act: 7.5641. Min Act: -0.1700
Data Index: 5221826 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0016. Min Range: -8.0016
Max Act: 7.5641. Min Act: -0.1700
Data Index: 2703087 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0016. Min Range: -8.0016
Max Act: 7.5641. Min Act: -0.1700
Data Index: 2181823 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19