Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4970 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6333. Min Range: -8.6333
Max Act: 8.6333. Min Act: -0.1700
Data Index: 6708357 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6333. Min Range: -8.6333
Max Act: 8.6333. Min Act: -0.1700
Data Index: 1392352 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6333. Min Range: -8.6333
Max Act: 8.5708. Min Act: -0.1700
Data Index: 6042065 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6333. Min Range: -8.6333
Max Act: 8.5708. Min Act: -0.1700
Data Index: 7874411 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6333. Min Range: -8.6333
Max Act: 8.2583. Min Act: -0.1700
Data Index: 26152 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6333. Min Range: -8.6333
Max Act: 8.3208. Min Act: -0.1700
Data Index: 4445938 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6333. Min Range: -8.6333
Max Act: 8.2583. Min Act: -0.1700
Data Index: 323629 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6333. Min Range: -8.6333
Max Act: 8.2583. Min Act: -0.1700
Data Index: 1869376 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6333. Min Range: -8.6333
Max Act: 8.1958. Min Act: -0.1700
Data Index: 1036801 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6333. Min Range: -8.6333
Max Act: 8.1333. Min Act: -0.1700
Data Index: 7137163 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6333. Min Range: -8.6333
Max Act: 8.1333. Min Act: -0.1700
Data Index: 3333896 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6333. Min Range: -8.6333
Max Act: 8.0708. Min Act: -0.1700
Data Index: 3430927 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6333. Min Range: -8.6333
Max Act: 8.0395. Min Act: -0.1700
Data Index: 2375969 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6333. Min Range: -8.6333
Max Act: 8.0083. Min Act: -0.1700
Data Index: 4740783 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6333. Min Range: -8.6333
Max Act: 8.0083. Min Act: -0.1700
Data Index: 1937447 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6333. Min Range: -8.6333
Max Act: 7.9770. Min Act: -0.1700
Data Index: 5277268 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6333. Min Range: -8.6333
Max Act: 7.8833. Min Act: -0.1700
Data Index: 5766231 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6333. Min Range: -8.6333
Max Act: 7.9458. Min Act: -0.1700
Data Index: 7314906 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6333. Min Range: -8.6333
Max Act: 7.8520. Min Act: -0.1700
Data Index: 6854383 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6333. Min Range: -8.6333
Max Act: 7.8520. Min Act: -0.1700
Data Index: 5508940 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19