Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2170 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0637. Min Range: -5.0637
Max Act: 5.0637. Min Act: -0.1700
Data Index: 3758115 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0637. Min Range: -5.0637
Max Act: 5.0637. Min Act: -0.1700
Data Index: 5994095 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0637. Min Range: -5.0637
Max Act: 4.9387. Min Act: -0.1700
Data Index: 7765008 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0637. Min Range: -5.0637
Max Act: 4.9387. Min Act: -0.1700
Data Index: 7744093 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0637. Min Range: -5.0637
Max Act: 4.8449. Min Act: -0.1700
Data Index: 6436490 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0637. Min Range: -5.0637
Max Act: 4.8449. Min Act: -0.1700
Data Index: 726950 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0637. Min Range: -5.0637
Max Act: 4.8137. Min Act: -0.1700
Data Index: 135610 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0637. Min Range: -5.0637
Max Act: 4.7824. Min Act: -0.1700
Data Index: 7013435 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0637. Min Range: -5.0637
Max Act: 4.7512. Min Act: -0.1700
Data Index: 7765007 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0637. Min Range: -5.0637
Max Act: 4.7512. Min Act: -0.1700
Data Index: 7744094 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0637. Min Range: -5.0637
Max Act: 4.7512. Min Act: -0.1700
Data Index: 4560971 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0637. Min Range: -5.0637
Max Act: 4.7199. Min Act: -0.1700
Data Index: 8026804 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0637. Min Range: -5.0637
Max Act: 4.7199. Min Act: -0.1700
Data Index: 6696499 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0637. Min Range: -5.0637
Max Act: 4.6887. Min Act: -0.1700
Data Index: 7640144 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0637. Min Range: -5.0637
Max Act: 4.6574. Min Act: -0.1700
Data Index: 1654623 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0637. Min Range: -5.0637
Max Act: 4.6887. Min Act: -0.1700
Data Index: 1746983 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0637. Min Range: -5.0637
Max Act: 4.6887. Min Act: -0.1700
Data Index: 8026803 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0637. Min Range: -5.0637
Max Act: 4.6574. Min Act: -0.1700
Data Index: 5471256 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0637. Min Range: -5.0637
Max Act: 4.6574. Min Act: -0.1700
Data Index: 7744092 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0637. Min Range: -5.0637
Max Act: 4.5949. Min Act: -0.1689
Data Index: 6056150 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19