Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2971 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3706. Min Range: -6.3706
Max Act: 6.3706. Min Act: -0.1700
Data Index: 8759310 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3706. Min Range: -6.3706
Max Act: 6.1831. Min Act: -0.1700
Data Index: 1475927 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3706. Min Range: -6.3706
Max Act: 6.1519. Min Act: -0.1700
Data Index: 3305666 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3706. Min Range: -6.3706
Max Act: 6.0894. Min Act: -0.1700
Data Index: 8114557 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3706. Min Range: -6.3706
Max Act: 6.0581. Min Act: -0.1700
Data Index: 2909478 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3706. Min Range: -6.3706
Max Act: 6.0581. Min Act: -0.1700
Data Index: 6143750 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3706. Min Range: -6.3706
Max Act: 5.9956. Min Act: -0.1700
Data Index: 4721976 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3706. Min Range: -6.3706
Max Act: 5.9956. Min Act: -0.1700
Data Index: 8110803 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3706. Min Range: -6.3706
Max Act: 5.9644. Min Act: -0.1700
Data Index: 959484 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3706. Min Range: -6.3706
Max Act: 5.9644. Min Act: -0.1700
Data Index: 973013 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3706. Min Range: -6.3706
Max Act: 5.9644. Min Act: -0.1700
Data Index: 1684994 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3706. Min Range: -6.3706
Max Act: 5.9644. Min Act: -0.1700
Data Index: 669725 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3706. Min Range: -6.3706
Max Act: 5.9644. Min Act: -0.1700
Data Index: 4131756 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3706. Min Range: -6.3706
Max Act: 5.9331. Min Act: -0.1700
Data Index: 2863720 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3706. Min Range: -6.3706
Max Act: 5.9331. Min Act: -0.1700
Data Index: 6335316 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3706. Min Range: -6.3706
Max Act: 5.9331. Min Act: -0.1700
Data Index: 5088900 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3706. Min Range: -6.3706
Max Act: 5.9331. Min Act: -0.1700
Data Index: 6323033 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3706. Min Range: -6.3706
Max Act: 5.9019. Min Act: -0.1700
Data Index: 6877407 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3706. Min Range: -6.3706
Max Act: 5.9019. Min Act: -0.1700
Data Index: 3090178 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3706. Min Range: -6.3706
Max Act: 5.9019. Min Act: -0.1700
Data Index: 1897056 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19