Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4664 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0891. Min Range: -10.0891
Max Act: 10.0891. Min Act: -0.1700
Data Index: 1120923 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0891. Min Range: -10.0891
Max Act: 9.9016. Min Act: -0.1700
Data Index: 7870704 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0891. Min Range: -10.0891
Max Act: 9.7766. Min Act: -0.1700
Data Index: 2027715 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0891. Min Range: -10.0891
Max Act: 9.8391. Min Act: -0.1700
Data Index: 8185158 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0891. Min Range: -10.0891
Max Act: 9.9016. Min Act: -0.1700
Data Index: 1641034 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0891. Min Range: -10.0891
Max Act: 9.8391. Min Act: -0.1700
Data Index: 5792099 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0891. Min Range: -10.0891
Max Act: 9.8391. Min Act: -0.1700
Data Index: 5760147 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0891. Min Range: -10.0891
Max Act: 9.8391. Min Act: -0.1700
Data Index: 5611553 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0891. Min Range: -10.0891
Max Act: 9.7766. Min Act: -0.1700
Data Index: 4800983 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0891. Min Range: -10.0891
Max Act: 9.7766. Min Act: -0.1700
Data Index: 4779397 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0891. Min Range: -10.0891
Max Act: 9.7766. Min Act: -0.1700
Data Index: 873348 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0891. Min Range: -10.0891
Max Act: 9.6516. Min Act: -0.1700
Data Index: 7639303 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0891. Min Range: -10.0891
Max Act: 9.7141. Min Act: -0.1700
Data Index: 1788013 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0891. Min Range: -10.0891
Max Act: 9.7141. Min Act: -0.1700
Data Index: 5325190 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0891. Min Range: -10.0891
Max Act: 9.6516. Min Act: -0.1700
Data Index: 7188998 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0891. Min Range: -10.0891
Max Act: 9.6516. Min Act: -0.1700
Data Index: 3491323 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0891. Min Range: -10.0891
Max Act: 9.6516. Min Act: -0.1700
Data Index: 4963770 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0891. Min Range: -10.0891
Max Act: 9.5891. Min Act: -0.1700
Data Index: 2006753 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0891. Min Range: -10.0891
Max Act: 9.6516. Min Act: -0.1700
Data Index: 5258762 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0891. Min Range: -10.0891
Max Act: 9.5891. Min Act: -0.1700
Data Index: 6266356 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #19