Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 87 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1822. Min Range: -10.1822
Max Act: 10.1822. Min Act: -0.1700
Data Index: 5006692 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1822. Min Range: -10.1822
Max Act: 10.1197. Min Act: -0.1700
Data Index: 5293020 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1822. Min Range: -10.1822
Max Act: 10.0572. Min Act: -0.1700
Data Index: 453845 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1822. Min Range: -10.1822
Max Act: 10.1197. Min Act: -0.1700
Data Index: 4763858 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1822. Min Range: -10.1822
Max Act: 10.0572. Min Act: -0.1700
Data Index: 2666723 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1822. Min Range: -10.1822
Max Act: 10.0572. Min Act: -0.1700
Data Index: 1986205 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1822. Min Range: -10.1822
Max Act: 9.9947. Min Act: -0.1700
Data Index: 6036524 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1822. Min Range: -10.1822
Max Act: 9.9322. Min Act: -0.1700
Data Index: 5572985 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1822. Min Range: -10.1822
Max Act: 9.8697. Min Act: -0.1700
Data Index: 5508675 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1822. Min Range: -10.1822
Max Act: 9.8072. Min Act: -0.1700
Data Index: 2957980 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1822. Min Range: -10.1822
Max Act: 9.8072. Min Act: -0.1700
Data Index: 4035855 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1822. Min Range: -10.1822
Max Act: 9.7447. Min Act: -0.1700
Data Index: 86341 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1822. Min Range: -10.1822
Max Act: 9.7447. Min Act: -0.1700
Data Index: 1434029 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1822. Min Range: -10.1822
Max Act: 9.7447. Min Act: -0.1700
Data Index: 499089 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1822. Min Range: -10.1822
Max Act: 9.7447. Min Act: -0.1700
Data Index: 7784301 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1822. Min Range: -10.1822
Max Act: 9.7447. Min Act: -0.1700
Data Index: 5770617 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1822. Min Range: -10.1822
Max Act: 9.6822. Min Act: -0.1700
Data Index: 1559377 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1822. Min Range: -10.1822
Max Act: 9.7447. Min Act: -0.1700
Data Index: 2202233 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1822. Min Range: -10.1822
Max Act: 9.7447. Min Act: -0.1700
Data Index: 929805 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1822. Min Range: -10.1822
Max Act: 9.7447. Min Act: -0.1700
Data Index: 4132068 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #19