Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4273 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2958. Min Range: -6.2958
Max Act: 6.2958. Min Act: -0.1700
Data Index: 1602214 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2958. Min Range: -6.2958
Max Act: 6.2021. Min Act: -0.1700
Data Index: 6978581 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2958. Min Range: -6.2958
Max Act: 6.1708. Min Act: -0.1700
Data Index: 51393 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2958. Min Range: -6.2958
Max Act: 6.1708. Min Act: -0.1700
Data Index: 8163622 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2958. Min Range: -6.2958
Max Act: 6.1083. Min Act: -0.1700
Data Index: 7032472 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2958. Min Range: -6.2958
Max Act: 6.0771. Min Act: -0.1700
Data Index: 6286441 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2958. Min Range: -6.2958
Max Act: 6.0458. Min Act: -0.1700
Data Index: 6978584 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2958. Min Range: -6.2958
Max Act: 6.0146. Min Act: -0.1700
Data Index: 6382596 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2958. Min Range: -6.2958
Max Act: 5.9833. Min Act: -0.1700
Data Index: 6598722 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2958. Min Range: -6.2958
Max Act: 5.9208. Min Act: -0.1700
Data Index: 1196260 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2958. Min Range: -6.2958
Max Act: 5.9521. Min Act: -0.1700
Data Index: 6414828 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2958. Min Range: -6.2958
Max Act: 5.9521. Min Act: -0.1700
Data Index: 2457369 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2958. Min Range: -6.2958
Max Act: 5.9208. Min Act: -0.1700
Data Index: 1004916 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2958. Min Range: -6.2958
Max Act: 5.8896. Min Act: -0.1700
Data Index: 8105791 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2958. Min Range: -6.2958
Max Act: 5.8896. Min Act: -0.1700
Data Index: 6978579 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2958. Min Range: -6.2958
Max Act: 5.8896. Min Act: -0.1700
Data Index: 5690955 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2958. Min Range: -6.2958
Max Act: 5.8896. Min Act: -0.1700
Data Index: 3796794 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2958. Min Range: -6.2958
Max Act: 5.8583. Min Act: -0.1700
Data Index: 254252 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2958. Min Range: -6.2958
Max Act: 5.8271. Min Act: -0.1700
Data Index: 6668599 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2958. Min Range: -6.2958
Max Act: 5.8583. Min Act: -0.1700
Data Index: 7880819 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19