Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3086 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2718. Min Range: -6.2718
Max Act: 6.2718. Min Act: -0.1700
Data Index: 121696 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2718. Min Range: -6.2718
Max Act: 6.0218. Min Act: -0.1700
Data Index: 3579340 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2718. Min Range: -6.2718
Max Act: 6.0218. Min Act: -0.1700
Data Index: 7790949 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2718. Min Range: -6.2718
Max Act: 5.8968. Min Act: -0.1700
Data Index: 7763934 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2718. Min Range: -6.2718
Max Act: 5.8968. Min Act: -0.1700
Data Index: 8823049 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2718. Min Range: -6.2718
Max Act: 5.8655. Min Act: -0.1700
Data Index: 7238840 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2718. Min Range: -6.2718
Max Act: 5.8343. Min Act: -0.1700
Data Index: 3711209 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2718. Min Range: -6.2718
Max Act: 5.8030. Min Act: -0.1700
Data Index: 4269492 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2718. Min Range: -6.2718
Max Act: 5.7718. Min Act: -0.1700
Data Index: 597855 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2718. Min Range: -6.2718
Max Act: 5.7405. Min Act: -0.1700
Data Index: 844112 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2718. Min Range: -6.2718
Max Act: 5.7093. Min Act: -0.1700
Data Index: 1403683 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2718. Min Range: -6.2718
Max Act: 5.7093. Min Act: -0.1700
Data Index: 1117810 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2718. Min Range: -6.2718
Max Act: 5.7093. Min Act: -0.1700
Data Index: 4105382 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2718. Min Range: -6.2718
Max Act: 5.6780. Min Act: -0.1700
Data Index: 3907440 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2718. Min Range: -6.2718
Max Act: 5.6780. Min Act: -0.1700
Data Index: 4784652 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2718. Min Range: -6.2718
Max Act: 5.6468. Min Act: -0.1700
Data Index: 3315664 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2718. Min Range: -6.2718
Max Act: 5.6155. Min Act: -0.1700
Data Index: 6287453 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2718. Min Range: -6.2718
Max Act: 5.6155. Min Act: -0.1700
Data Index: 5849948 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2718. Min Range: -6.2718
Max Act: 5.6155. Min Act: -0.1700
Data Index: 24873 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2718. Min Range: -6.2718
Max Act: 5.5843. Min Act: -0.1700
Data Index: 652830 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #19