Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2438 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1997. Min Range: -4.1997
Max Act: 4.1997. Min Act: -0.1700
Data Index: 8406331 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1997. Min Range: -4.1997
Max Act: 4.1685. Min Act: -0.1700
Data Index: 5429056 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1997. Min Range: -4.1997
Max Act: 4.1685. Min Act: -0.1700
Data Index: 4218079 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1997. Min Range: -4.1997
Max Act: 4.1685. Min Act: -0.1700
Data Index: 5470913 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1997. Min Range: -4.1997
Max Act: 4.1060. Min Act: -0.1700
Data Index: 606789 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1997. Min Range: -4.1997
Max Act: 4.1060. Min Act: -0.1700
Data Index: 6167804 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1997. Min Range: -4.1997
Max Act: 4.0434. Min Act: -0.1700
Data Index: 1074571 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1997. Min Range: -4.1997
Max Act: 4.0747. Min Act: -0.1700
Data Index: 7546971 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1997. Min Range: -4.1997
Max Act: 4.0747. Min Act: -0.1700
Data Index: 1918298 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1997. Min Range: -4.1997
Max Act: 4.0747. Min Act: -0.1700
Data Index: 8363605 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1997. Min Range: -4.1997
Max Act: 4.0434. Min Act: -0.1700
Data Index: 6608058 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1997. Min Range: -4.1997
Max Act: 4.0434. Min Act: -0.1700
Data Index: 2734396 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1997. Min Range: -4.1997
Max Act: 4.0747. Min Act: -0.1700
Data Index: 6716935 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1997. Min Range: -4.1997
Max Act: 4.0122. Min Act: -0.1700
Data Index: 2242645 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1997. Min Range: -4.1997
Max Act: 4.0122. Min Act: -0.1700
Data Index: 8745864 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1997. Min Range: -4.1997
Max Act: 3.9809. Min Act: -0.1700
Data Index: 8318617 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1997. Min Range: -4.1997
Max Act: 3.9809. Min Act: -0.1700
Data Index: 5442784 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1997. Min Range: -4.1997
Max Act: 3.9809. Min Act: -0.1700
Data Index: 3562773 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1997. Min Range: -4.1997
Max Act: 3.9809. Min Act: -0.1700
Data Index: 267218 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1997. Min Range: -4.1997
Max Act: 3.9497. Min Act: -0.1700
Data Index: 7136251 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19