Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1861 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0867. Min Range: -5.0867
Max Act: 5.0867. Min Act: -0.1700
Data Index: 4134998 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0867. Min Range: -5.0867
Max Act: 5.0867. Min Act: -0.1700
Data Index: 3498219 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0867. Min Range: -5.0867
Max Act: 4.8992. Min Act: -0.1700
Data Index: 7117813 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0867. Min Range: -5.0867
Max Act: 4.6804. Min Act: -0.1700
Data Index: 8005877 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0867. Min Range: -5.0867
Max Act: 4.5867. Min Act: -0.1700
Data Index: 5539831 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0867. Min Range: -5.0867
Max Act: 4.5554. Min Act: -0.1700
Data Index: 321536 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0867. Min Range: -5.0867
Max Act: 4.5867. Min Act: -0.1700
Data Index: 8697530 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0867. Min Range: -5.0867
Max Act: 4.5554. Min Act: -0.1700
Data Index: 8503831 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0867. Min Range: -5.0867
Max Act: 4.5554. Min Act: -0.1700
Data Index: 5314218 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0867. Min Range: -5.0867
Max Act: 4.5242. Min Act: -0.1700
Data Index: 2667051 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0867. Min Range: -5.0867
Max Act: 4.4929. Min Act: -0.1700
Data Index: 1536958 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0867. Min Range: -5.0867
Max Act: 4.4929. Min Act: -0.1700
Data Index: 897668 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0867. Min Range: -5.0867
Max Act: 4.4617. Min Act: -0.1700
Data Index: 7273578 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0867. Min Range: -5.0867
Max Act: 4.4617. Min Act: -0.1700
Data Index: 3898682 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0867. Min Range: -5.0867
Max Act: 4.4929. Min Act: -0.1700
Data Index: 5303507 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0867. Min Range: -5.0867
Max Act: 4.4617. Min Act: -0.1700
Data Index: 6643669 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0867. Min Range: -5.0867
Max Act: 4.4617. Min Act: -0.1700
Data Index: 8158028 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0867. Min Range: -5.0867
Max Act: 4.4304. Min Act: -0.1700
Data Index: 769806 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0867. Min Range: -5.0867
Max Act: 4.3992. Min Act: -0.1700
Data Index: 3877143 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0867. Min Range: -5.0867
Max Act: 4.3679. Min Act: -0.1700
Data Index: 1038879 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #19