Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3552 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5812. Min Range: -7.5812
Max Act: 7.5187. Min Act: -0.1700
Data Index: 4660387 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5812. Min Range: -7.5812
Max Act: 7.5812. Min Act: -0.1700
Data Index: 1333399 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5812. Min Range: -7.5812
Max Act: 7.2062. Min Act: -0.1700
Data Index: 1733255 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5812. Min Range: -7.5812
Max Act: 7.2062. Min Act: -0.1700
Data Index: 335188 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5812. Min Range: -7.5812
Max Act: 7.2062. Min Act: -0.1700
Data Index: 2113741 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5812. Min Range: -7.5812
Max Act: 7.1124. Min Act: -0.1700
Data Index: 33376 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5812. Min Range: -7.5812
Max Act: 7.0812. Min Act: -0.1700
Data Index: 3083337 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5812. Min Range: -7.5812
Max Act: 6.9249. Min Act: -0.1700
Data Index: 1018666 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5812. Min Range: -7.5812
Max Act: 6.9249. Min Act: -0.1700
Data Index: 207624 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5812. Min Range: -7.5812
Max Act: 6.8937. Min Act: -0.1700
Data Index: 6429870 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5812. Min Range: -7.5812
Max Act: 6.8937. Min Act: -0.1700
Data Index: 8394718 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5812. Min Range: -7.5812
Max Act: 6.8937. Min Act: -0.1700
Data Index: 3486487 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5812. Min Range: -7.5812
Max Act: 6.8312. Min Act: -0.1700
Data Index: 4065618 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5812. Min Range: -7.5812
Max Act: 6.8312. Min Act: -0.1700
Data Index: 2395131 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5812. Min Range: -7.5812
Max Act: 6.7999. Min Act: -0.1700
Data Index: 2004983 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5812. Min Range: -7.5812
Max Act: 6.7999. Min Act: -0.1700
Data Index: 1408945 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5812. Min Range: -7.5812
Max Act: 6.7687. Min Act: -0.1700
Data Index: 2008545 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5812. Min Range: -7.5812
Max Act: 6.7374. Min Act: -0.1700
Data Index: 33377 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5812. Min Range: -7.5812
Max Act: 6.7374. Min Act: -0.1700
Data Index: 4091336 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5812. Min Range: -7.5812
Max Act: 6.7062. Min Act: -0.1700
Data Index: 4538904 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #19