Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3667 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2794. Min Range: -6.2794
Max Act: 6.2794. Min Act: -0.1700
Data Index: 1109873 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2794. Min Range: -6.2794
Max Act: 5.9981. Min Act: -0.1700
Data Index: 7130727 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2794. Min Range: -6.2794
Max Act: 5.9669. Min Act: -0.1700
Data Index: 6661137 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2794. Min Range: -6.2794
Max Act: 5.9669. Min Act: -0.1700
Data Index: 552908 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2794. Min Range: -6.2794
Max Act: 5.9669. Min Act: -0.1700
Data Index: 6073180 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2794. Min Range: -6.2794
Max Act: 5.9356. Min Act: -0.1700
Data Index: 2175356 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2794. Min Range: -6.2794
Max Act: 5.8731. Min Act: -0.1700
Data Index: 2423942 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2794. Min Range: -6.2794
Max Act: 5.8419. Min Act: -0.1700
Data Index: 7407853 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2794. Min Range: -6.2794
Max Act: 5.8731. Min Act: -0.1700
Data Index: 7270647 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2794. Min Range: -6.2794
Max Act: 5.8419. Min Act: -0.1700
Data Index: 3832265 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2794. Min Range: -6.2794
Max Act: 5.8106. Min Act: -0.1700
Data Index: 4079328 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2794. Min Range: -6.2794
Max Act: 5.8106. Min Act: -0.1700
Data Index: 6675137 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2794. Min Range: -6.2794
Max Act: 5.7794. Min Act: -0.1700
Data Index: 3243945 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2794. Min Range: -6.2794
Max Act: 5.8106. Min Act: -0.1700
Data Index: 23645 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2794. Min Range: -6.2794
Max Act: 5.8106. Min Act: -0.1700
Data Index: 5201068 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2794. Min Range: -6.2794
Max Act: 5.7794. Min Act: -0.1700
Data Index: 92706 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2794. Min Range: -6.2794
Max Act: 5.7794. Min Act: -0.1700
Data Index: 583138 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2794. Min Range: -6.2794
Max Act: 5.7794. Min Act: -0.1700
Data Index: 4070761 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2794. Min Range: -6.2794
Max Act: 5.7794. Min Act: -0.1700
Data Index: 5896563 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2794. Min Range: -6.2794
Max Act: 5.7794. Min Act: -0.1700
Data Index: 1068767 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #19