Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6184 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5898. Min Range: -6.5898
Max Act: 6.5898. Min Act: -0.1700
Data Index: 695673 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5898. Min Range: -6.5898
Max Act: 5.9335. Min Act: -0.1700
Data Index: 3509483 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5898. Min Range: -6.5898
Max Act: 5.9023. Min Act: -0.1700
Data Index: 5204304 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5898. Min Range: -6.5898
Max Act: 5.9335. Min Act: -0.1700
Data Index: 3877839 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5898. Min Range: -6.5898
Max Act: 5.9023. Min Act: -0.1700
Data Index: 3520463 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5898. Min Range: -6.5898
Max Act: 5.7773. Min Act: -0.1700
Data Index: 3485659 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5898. Min Range: -6.5898
Max Act: 5.7460. Min Act: -0.1700
Data Index: 699254 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5898. Min Range: -6.5898
Max Act: 5.7460. Min Act: -0.1700
Data Index: 6963071 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5898. Min Range: -6.5898
Max Act: 5.6835. Min Act: -0.1700
Data Index: 5267610 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5898. Min Range: -6.5898
Max Act: 5.6523. Min Act: -0.1700
Data Index: 7683601 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5898. Min Range: -6.5898
Max Act: 5.6210. Min Act: -0.1700
Data Index: 236378 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5898. Min Range: -6.5898
Max Act: 5.6210. Min Act: -0.1700
Data Index: 7261411 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5898. Min Range: -6.5898
Max Act: 5.6210. Min Act: -0.1700
Data Index: 2307007 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5898. Min Range: -6.5898
Max Act: 5.6210. Min Act: -0.1700
Data Index: 3924635 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5898. Min Range: -6.5898
Max Act: 5.6210. Min Act: -0.1700
Data Index: 8386801 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5898. Min Range: -6.5898
Max Act: 5.6210. Min Act: -0.1700
Data Index: 6899101 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5898. Min Range: -6.5898
Max Act: 5.5898. Min Act: -0.1700
Data Index: 525223 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5898. Min Range: -6.5898
Max Act: 5.6210. Min Act: -0.1700
Data Index: 8382661 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5898. Min Range: -6.5898
Max Act: 5.6210. Min Act: -0.1700
Data Index: 7594110 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5898. Min Range: -6.5898
Max Act: 5.5898. Min Act: -0.1700
Data Index: 1054731 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19