Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3808 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1284. Min Range: -5.1284
Max Act: 5.1284. Min Act: -0.1700
Data Index: 778678 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1284. Min Range: -5.1284
Max Act: 4.7846. Min Act: -0.1700
Data Index: 7437352 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1284. Min Range: -5.1284
Max Act: 4.7846. Min Act: -0.1700
Data Index: 8387836 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1284. Min Range: -5.1284
Max Act: 4.7534. Min Act: -0.1700
Data Index: 4356960 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1284. Min Range: -5.1284
Max Act: 4.7846. Min Act: -0.1700
Data Index: 5467371 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1284. Min Range: -5.1284
Max Act: 4.7534. Min Act: -0.1700
Data Index: 3102411 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1284. Min Range: -5.1284
Max Act: 4.7221. Min Act: -0.1700
Data Index: 4154857 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1284. Min Range: -5.1284
Max Act: 4.6909. Min Act: -0.1700
Data Index: 5496576 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1284. Min Range: -5.1284
Max Act: 4.6596. Min Act: -0.1700
Data Index: 4727615 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1284. Min Range: -5.1284
Max Act: 4.6284. Min Act: -0.1700
Data Index: 1169536 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1284. Min Range: -5.1284
Max Act: 4.6596. Min Act: -0.1700
Data Index: 6286332 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1284. Min Range: -5.1284
Max Act: 4.6284. Min Act: -0.1700
Data Index: 6968548 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1284. Min Range: -5.1284
Max Act: 4.5971. Min Act: -0.1700
Data Index: 202050 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1284. Min Range: -5.1284
Max Act: 4.6284. Min Act: -0.1700
Data Index: 8274687 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1284. Min Range: -5.1284
Max Act: 4.5659. Min Act: -0.1700
Data Index: 470101 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1284. Min Range: -5.1284
Max Act: 4.5971. Min Act: -0.1700
Data Index: 7511887 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1284. Min Range: -5.1284
Max Act: 4.5971. Min Act: -0.1700
Data Index: 1746864 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1284. Min Range: -5.1284
Max Act: 4.5659. Min Act: -0.1700
Data Index: 5350371 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1284. Min Range: -5.1284
Max Act: 4.5971. Min Act: -0.1700
Data Index: 8606601 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1284. Min Range: -5.1284
Max Act: 4.5971. Min Act: -0.1700
Data Index: 8644401 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #19