Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1116 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1404. Min Range: -8.1404
Max Act: 8.1404. Min Act: -0.1700
Data Index: 4242454 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1404. Min Range: -8.1404
Max Act: 8.0779. Min Act: -0.1700
Data Index: 6118117 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1404. Min Range: -8.1404
Max Act: 7.8904. Min Act: -0.1700
Data Index: 1168039 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1404. Min Range: -8.1404
Max Act: 7.8904. Min Act: -0.1700
Data Index: 2887130 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1404. Min Range: -8.1404
Max Act: 7.7654. Min Act: -0.1700
Data Index: 8197071 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1404. Min Range: -8.1404
Max Act: 7.7029. Min Act: -0.1700
Data Index: 7638845 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1404. Min Range: -8.1404
Max Act: 7.7654. Min Act: -0.1700
Data Index: 1454749 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1404. Min Range: -8.1404
Max Act: 7.7654. Min Act: -0.1700
Data Index: 6001835 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1404. Min Range: -8.1404
Max Act: 7.7654. Min Act: -0.1700
Data Index: 4584466 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1404. Min Range: -8.1404
Max Act: 7.8279. Min Act: -0.1700
Data Index: 3774450 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1404. Min Range: -8.1404
Max Act: 7.7029. Min Act: -0.1700
Data Index: 2538206 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1404. Min Range: -8.1404
Max Act: 7.7029. Min Act: -0.1700
Data Index: 91856 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1404. Min Range: -8.1404
Max Act: 7.7029. Min Act: -0.1700
Data Index: 7970264 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1404. Min Range: -8.1404
Max Act: 7.7029. Min Act: -0.1700
Data Index: 1022648 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1404. Min Range: -8.1404
Max Act: 7.7029. Min Act: -0.1700
Data Index: 6098292 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1404. Min Range: -8.1404
Max Act: 7.6404. Min Act: -0.1700
Data Index: 5962420 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1404. Min Range: -8.1404
Max Act: 7.7029. Min Act: -0.1700
Data Index: 4537247 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1404. Min Range: -8.1404
Max Act: 7.5779. Min Act: -0.1700
Data Index: 1165293 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1404. Min Range: -8.1404
Max Act: 7.5779. Min Act: -0.1700
Data Index: 3869405 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1404. Min Range: -8.1404
Max Act: 7.5779. Min Act: -0.1700
Data Index: 6774018 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #19