Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5675 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1081. Min Range: -6.1081
Max Act: 6.1081. Min Act: -0.1700
Data Index: 5747507 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1081. Min Range: -6.1081
Max Act: 6.1081. Min Act: -0.1700
Data Index: 1618598 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1081. Min Range: -6.1081
Max Act: 6.0144. Min Act: -0.1700
Data Index: 3080572 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1081. Min Range: -6.1081
Max Act: 5.9831. Min Act: -0.1700
Data Index: 3396004 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1081. Min Range: -6.1081
Max Act: 6.0456. Min Act: -0.1700
Data Index: 1815991 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1081. Min Range: -6.1081
Max Act: 5.9831. Min Act: -0.1700
Data Index: 2581179 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1081. Min Range: -6.1081
Max Act: 5.9831. Min Act: -0.1700
Data Index: 4586112 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1081. Min Range: -6.1081
Max Act: 5.9831. Min Act: -0.1700
Data Index: 5291477 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1081. Min Range: -6.1081
Max Act: 5.9831. Min Act: -0.1700
Data Index: 5253561 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1081. Min Range: -6.1081
Max Act: 5.9831. Min Act: -0.1700
Data Index: 1655026 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1081. Min Range: -6.1081
Max Act: 5.9519. Min Act: -0.1700
Data Index: 5486920 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1081. Min Range: -6.1081
Max Act: 5.9519. Min Act: -0.1700
Data Index: 50623 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1081. Min Range: -6.1081
Max Act: 5.9206. Min Act: -0.1700
Data Index: 4827156 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1081. Min Range: -6.1081
Max Act: 5.8894. Min Act: -0.1700
Data Index: 111787 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1081. Min Range: -6.1081
Max Act: 5.9206. Min Act: -0.1700
Data Index: 8779288 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1081. Min Range: -6.1081
Max Act: 5.9206. Min Act: -0.1700
Data Index: 5249041 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1081. Min Range: -6.1081
Max Act: 5.9206. Min Act: -0.1700
Data Index: 5183861 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1081. Min Range: -6.1081
Max Act: 5.9206. Min Act: -0.1700
Data Index: 5141531 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1081. Min Range: -6.1081
Max Act: 5.8894. Min Act: -0.1700
Data Index: 4927981 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1081. Min Range: -6.1081
Max Act: 5.8894. Min Act: -0.1700
Data Index: 3105145 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19