Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3559 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1039. Min Range: -6.1039
Max Act: 6.1039. Min Act: -0.1700
Data Index: 4643476 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1039. Min Range: -6.1039
Max Act: 6.0726. Min Act: -0.1700
Data Index: 1537832 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1039. Min Range: -6.1039
Max Act: 5.9789. Min Act: -0.1700
Data Index: 3540188 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1039. Min Range: -6.1039
Max Act: 6.0101. Min Act: -0.1700
Data Index: 583928 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1039. Min Range: -6.1039
Max Act: 5.9789. Min Act: -0.1700
Data Index: 7567011 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1039. Min Range: -6.1039
Max Act: 5.9476. Min Act: -0.1700
Data Index: 5760197 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1039. Min Range: -6.1039
Max Act: 5.9164. Min Act: -0.1700
Data Index: 179363 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1039. Min Range: -6.1039
Max Act: 5.9164. Min Act: -0.1700
Data Index: 7707545 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1039. Min Range: -6.1039
Max Act: 5.8851. Min Act: -0.1700
Data Index: 3760110 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1039. Min Range: -6.1039
Max Act: 5.8539. Min Act: -0.1700
Data Index: 3240332 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1039. Min Range: -6.1039
Max Act: 5.8539. Min Act: -0.1700
Data Index: 4876846 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1039. Min Range: -6.1039
Max Act: 5.8226. Min Act: -0.1700
Data Index: 5761300 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1039. Min Range: -6.1039
Max Act: 5.8226. Min Act: -0.1700
Data Index: 4505910 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1039. Min Range: -6.1039
Max Act: 5.7914. Min Act: -0.1700
Data Index: 4898360 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1039. Min Range: -6.1039
Max Act: 5.8226. Min Act: -0.1700
Data Index: 1782106 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1039. Min Range: -6.1039
Max Act: 5.7914. Min Act: -0.1700
Data Index: 5629148 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1039. Min Range: -6.1039
Max Act: 5.7914. Min Act: -0.1700
Data Index: 7050514 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1039. Min Range: -6.1039
Max Act: 5.7601. Min Act: -0.1700
Data Index: 3450671 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1039. Min Range: -6.1039
Max Act: 5.7601. Min Act: -0.1700
Data Index: 2145086 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1039. Min Range: -6.1039
Max Act: 5.7601. Min Act: -0.1700
Data Index: 4072428 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #19