Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 705 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3687. Min Range: -4.3687
Max Act: 4.3687. Min Act: -0.1700
Data Index: 7200447 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3687. Min Range: -4.3687
Max Act: 4.1499. Min Act: -0.1700
Data Index: 6765284 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3687. Min Range: -4.3687
Max Act: 4.0874. Min Act: -0.1700
Data Index: 5941787 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3687. Min Range: -4.3687
Max Act: 4.0874. Min Act: -0.1700
Data Index: 1625827 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3687. Min Range: -4.3687
Max Act: 4.0561. Min Act: -0.1700
Data Index: 7541576 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3687. Min Range: -4.3687
Max Act: 3.9311. Min Act: -0.1700
Data Index: 8473528 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3687. Min Range: -4.3687
Max Act: 3.8998. Min Act: -0.1700
Data Index: 5566427 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3687. Min Range: -4.3687
Max Act: 3.8373. Min Act: -0.1700
Data Index: 7200443 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3687. Min Range: -4.3687
Max Act: 3.8685. Min Act: -0.1700
Data Index: 3463582 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3687. Min Range: -4.3687
Max Act: 3.8685. Min Act: -0.1700
Data Index: 4156331 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3687. Min Range: -4.3687
Max Act: 3.8373. Min Act: -0.1700
Data Index: 5341893 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3687. Min Range: -4.3687
Max Act: 3.8373. Min Act: -0.1700
Data Index: 7263836 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3687. Min Range: -4.3687
Max Act: 3.8373. Min Act: -0.1700
Data Index: 6668282 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3687. Min Range: -4.3687
Max Act: 3.7747. Min Act: -0.1700
Data Index: 7200445 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3687. Min Range: -4.3687
Max Act: 3.8060. Min Act: -0.1700
Data Index: 1524418 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3687. Min Range: -4.3687
Max Act: 3.7747. Min Act: -0.1700
Data Index: 6236018 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3687. Min Range: -4.3687
Max Act: 3.7747. Min Act: -0.1700
Data Index: 4296812 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3687. Min Range: -4.3687
Max Act: 3.7747. Min Act: -0.1700
Data Index: 6862242 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3687. Min Range: -4.3687
Max Act: 3.7278. Min Act: -0.1700
Data Index: 196214 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3687. Min Range: -4.3687
Max Act: 3.7435. Min Act: -0.1700
Data Index: 5785443 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #19