Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5916 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0057. Min Range: -8.0057
Max Act: 7.9744. Min Act: -0.1700
Data Index: 4972464 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0057. Min Range: -8.0057
Max Act: 8.0057. Min Act: -0.1700
Data Index: 6425850 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0057. Min Range: -8.0057
Max Act: 7.9432. Min Act: -0.1700
Data Index: 3386045 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0057. Min Range: -8.0057
Max Act: 7.7244. Min Act: -0.1700
Data Index: 6249159 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0057. Min Range: -8.0057
Max Act: 7.6307. Min Act: -0.1700
Data Index: 8501932 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0057. Min Range: -8.0057
Max Act: 7.5682. Min Act: -0.1700
Data Index: 5983434 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0057. Min Range: -8.0057
Max Act: 7.5682. Min Act: -0.1700
Data Index: 4868169 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0057. Min Range: -8.0057
Max Act: 7.5369. Min Act: -0.1700
Data Index: 1469030 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0057. Min Range: -8.0057
Max Act: 7.5369. Min Act: -0.1700
Data Index: 4443757 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0057. Min Range: -8.0057
Max Act: 7.5369. Min Act: -0.1700
Data Index: 8208458 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0057. Min Range: -8.0057
Max Act: 7.5057. Min Act: -0.1700
Data Index: 8612785 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0057. Min Range: -8.0057
Max Act: 7.5057. Min Act: -0.1700
Data Index: 146130 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0057. Min Range: -8.0057
Max Act: 7.5369. Min Act: -0.1700
Data Index: 4022934 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0057. Min Range: -8.0057
Max Act: 7.4744. Min Act: -0.1700
Data Index: 1395539 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0057. Min Range: -8.0057
Max Act: 7.4744. Min Act: -0.1700
Data Index: 7807920 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0057. Min Range: -8.0057
Max Act: 7.4432. Min Act: -0.1700
Data Index: 3450893 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0057. Min Range: -8.0057
Max Act: 7.4432. Min Act: -0.1700
Data Index: 5341006 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0057. Min Range: -8.0057
Max Act: 7.4432. Min Act: -0.1700
Data Index: 7249435 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0057. Min Range: -8.0057
Max Act: 7.4432. Min Act: -0.1700
Data Index: 5175488 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0057. Min Range: -8.0057
Max Act: 7.4432. Min Act: -0.1700
Data Index: 3050741 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19