Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1868 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1992. Min Range: -8.1992
Max Act: 8.1992. Min Act: -0.1700
Data Index: 6992861 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1992. Min Range: -8.1992
Max Act: 8.0742. Min Act: -0.1700
Data Index: 6255479 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1992. Min Range: -8.1992
Max Act: 8.0742. Min Act: -0.1700
Data Index: 4678057 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1992. Min Range: -8.1992
Max Act: 7.9492. Min Act: -0.1700
Data Index: 3776827 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1992. Min Range: -8.1992
Max Act: 7.9492. Min Act: -0.1700
Data Index: 4237593 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1992. Min Range: -8.1992
Max Act: 7.8867. Min Act: -0.1700
Data Index: 1825493 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1992. Min Range: -8.1992
Max Act: 7.8867. Min Act: -0.1700
Data Index: 4038134 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1992. Min Range: -8.1992
Max Act: 7.8242. Min Act: -0.1700
Data Index: 5842359 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1992. Min Range: -8.1992
Max Act: 7.8242. Min Act: -0.1700
Data Index: 7797442 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1992. Min Range: -8.1992
Max Act: 7.8242. Min Act: -0.1700
Data Index: 7712099 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1992. Min Range: -8.1992
Max Act: 7.7617. Min Act: -0.1700
Data Index: 4196606 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1992. Min Range: -8.1992
Max Act: 7.6992. Min Act: -0.1700
Data Index: 1834165 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1992. Min Range: -8.1992
Max Act: 7.7617. Min Act: -0.1700
Data Index: 4104191 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1992. Min Range: -8.1992
Max Act: 7.7617. Min Act: -0.1700
Data Index: 5534564 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1992. Min Range: -8.1992
Max Act: 7.7617. Min Act: -0.1700
Data Index: 7322887 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1992. Min Range: -8.1992
Max Act: 7.7617. Min Act: -0.1700
Data Index: 7661279 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1992. Min Range: -8.1992
Max Act: 7.6992. Min Act: -0.1700
Data Index: 2917756 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1992. Min Range: -8.1992
Max Act: 7.6367. Min Act: -0.1700
Data Index: 1526132 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1992. Min Range: -8.1992
Max Act: 7.6367. Min Act: -0.1700
Data Index: 5172335 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1992. Min Range: -8.1992
Max Act: 7.6992. Min Act: -0.1700
Data Index: 7165016 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #19