Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3659 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3737. Min Range: -3.3737
Max Act: 3.3737. Min Act: -0.1700
Data Index: 3122122 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3737. Min Range: -3.3737
Max Act: 3.3737. Min Act: -0.1700
Data Index: 4558486 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3737. Min Range: -3.3737
Max Act: 3.3737. Min Act: -0.1700
Data Index: 3308769 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3737. Min Range: -3.3737
Max Act: 3.3737. Min Act: -0.1700
Data Index: 1200902 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3737. Min Range: -3.3737
Max Act: 3.3737. Min Act: -0.1700
Data Index: 1200905 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3737. Min Range: -3.3737
Max Act: 3.3423. Min Act: -0.1700
Data Index: 6207291 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3737. Min Range: -3.3737
Max Act: 3.3423. Min Act: -0.1700
Data Index: 1402965 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3737. Min Range: -3.3737
Max Act: 3.3423. Min Act: -0.1700
Data Index: 1991103 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3737. Min Range: -3.3737
Max Act: 3.3423. Min Act: -0.1700
Data Index: 5292328 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3737. Min Range: -3.3737
Max Act: 3.3423. Min Act: -0.1700
Data Index: 3159574 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3737. Min Range: -3.3737
Max Act: 3.3423. Min Act: -0.1700
Data Index: 2286661 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3737. Min Range: -3.3737
Max Act: 3.3423. Min Act: -0.1700
Data Index: 1200904 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3737. Min Range: -3.3737
Max Act: 3.3266. Min Act: -0.1700
Data Index: 7497722 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3737. Min Range: -3.3737
Max Act: 3.3266. Min Act: -0.1700
Data Index: 4186920 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3737. Min Range: -3.3737
Max Act: 3.3109. Min Act: -0.1700
Data Index: 6260980 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3737. Min Range: -3.3737
Max Act: 3.3109. Min Act: -0.1700
Data Index: 1200906 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3737. Min Range: -3.3737
Max Act: 3.3266. Min Act: -0.1700
Data Index: 3313795 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3737. Min Range: -3.3737
Max Act: 3.3109. Min Act: -0.1700
Data Index: 2073122 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3737. Min Range: -3.3737
Max Act: 3.2952. Min Act: -0.1700
Data Index: 3985983 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3737. Min Range: -3.3737
Max Act: 3.3109. Min Act: -0.1700
Data Index: 3855697 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19