Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3504 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7774. Min Range: -5.7774
Max Act: 5.7774. Min Act: -0.1700
Data Index: 1168970 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7774. Min Range: -5.7774
Max Act: 5.4024. Min Act: -0.1700
Data Index: 438183 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7774. Min Range: -5.7774
Max Act: 5.3086. Min Act: -0.1700
Data Index: 294609 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7774. Min Range: -5.7774
Max Act: 5.2774. Min Act: -0.1700
Data Index: 1874029 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7774. Min Range: -5.7774
Max Act: 5.2149. Min Act: -0.1700
Data Index: 3312159 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7774. Min Range: -5.7774
Max Act: 5.1524. Min Act: -0.1700
Data Index: 6931422 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7774. Min Range: -5.7774
Max Act: 5.1836. Min Act: -0.1700
Data Index: 6957958 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7774. Min Range: -5.7774
Max Act: 5.1836. Min Act: -0.1700
Data Index: 7572850 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7774. Min Range: -5.7774
Max Act: 5.1524. Min Act: -0.1700
Data Index: 5332813 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7774. Min Range: -5.7774
Max Act: 5.1211. Min Act: -0.1700
Data Index: 3542822 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7774. Min Range: -5.7774
Max Act: 5.1211. Min Act: -0.1700
Data Index: 7613817 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7774. Min Range: -5.7774
Max Act: 5.0899. Min Act: -0.1700
Data Index: 1374881 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7774. Min Range: -5.7774
Max Act: 5.1211. Min Act: -0.1700
Data Index: 3891012 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7774. Min Range: -5.7774
Max Act: 5.0899. Min Act: -0.1700
Data Index: 162141 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7774. Min Range: -5.7774
Max Act: 5.0899. Min Act: -0.1700
Data Index: 5129681 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7774. Min Range: -5.7774
Max Act: 5.0586. Min Act: -0.1700
Data Index: 1380077 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7774. Min Range: -5.7774
Max Act: 5.0274. Min Act: -0.1700
Data Index: 5905139 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7774. Min Range: -5.7774
Max Act: 5.0274. Min Act: -0.1700
Data Index: 5629741 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7774. Min Range: -5.7774
Max Act: 4.9961. Min Act: -0.1700
Data Index: 5429462 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7774. Min Range: -5.7774
Max Act: 4.9961. Min Act: -0.1700
Data Index: 2465691 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19