Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1842 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1922. Min Range: -5.1922
Max Act: 5.1922. Min Act: -0.1700
Data Index: 265633 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1922. Min Range: -5.1922
Max Act: 5.1610. Min Act: -0.1700
Data Index: 5203841 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1922. Min Range: -5.1922
Max Act: 5.0985. Min Act: -0.1700
Data Index: 5393017 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1922. Min Range: -5.1922
Max Act: 5.0672. Min Act: -0.1700
Data Index: 4441804 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1922. Min Range: -5.1922
Max Act: 5.0672. Min Act: -0.1700
Data Index: 5388562 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1922. Min Range: -5.1922
Max Act: 5.0360. Min Act: -0.1700
Data Index: 665092 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1922. Min Range: -5.1922
Max Act: 5.0047. Min Act: -0.1700
Data Index: 2433141 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1922. Min Range: -5.1922
Max Act: 5.0047. Min Act: -0.1700
Data Index: 6961606 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1922. Min Range: -5.1922
Max Act: 5.0047. Min Act: -0.1700
Data Index: 2192504 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1922. Min Range: -5.1922
Max Act: 4.9735. Min Act: -0.1700
Data Index: 4269807 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1922. Min Range: -5.1922
Max Act: 4.9422. Min Act: -0.1700
Data Index: 4159126 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1922. Min Range: -5.1922
Max Act: 4.9422. Min Act: -0.1700
Data Index: 4716400 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1922. Min Range: -5.1922
Max Act: 4.9422. Min Act: -0.1700
Data Index: 6122722 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1922. Min Range: -5.1922
Max Act: 4.9422. Min Act: -0.1700
Data Index: 2713293 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1922. Min Range: -5.1922
Max Act: 4.9110. Min Act: -0.1700
Data Index: 7788132 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1922. Min Range: -5.1922
Max Act: 4.9110. Min Act: -0.1700
Data Index: 3827651 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1922. Min Range: -5.1922
Max Act: 4.9110. Min Act: -0.1700
Data Index: 6639288 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1922. Min Range: -5.1922
Max Act: 4.8485. Min Act: -0.1700
Data Index: 3895655 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1922. Min Range: -5.1922
Max Act: 4.8797. Min Act: -0.1700
Data Index: 6456205 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1922. Min Range: -5.1922
Max Act: 4.8797. Min Act: -0.1700
Data Index: 6459526 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #19