Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3421 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6146. Min Range: -7.6146
Max Act: 7.6146. Min Act: -0.1700
Data Index: 2849220 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6146. Min Range: -7.6146
Max Act: 7.5521. Min Act: -0.1700
Data Index: 7362887 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6146. Min Range: -7.6146
Max Act: 7.2396. Min Act: -0.1700
Data Index: 5193315 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6146. Min Range: -7.6146
Max Act: 7.2396. Min Act: -0.1700
Data Index: 2582412 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6146. Min Range: -7.6146
Max Act: 7.2083. Min Act: -0.1700
Data Index: 5031606 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6146. Min Range: -7.6146
Max Act: 7.2083. Min Act: -0.1700
Data Index: 2542313 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6146. Min Range: -7.6146
Max Act: 7.1771. Min Act: -0.1700
Data Index: 861479 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6146. Min Range: -7.6146
Max Act: 7.1146. Min Act: -0.1700
Data Index: 4703122 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6146. Min Range: -7.6146
Max Act: 7.0833. Min Act: -0.1700
Data Index: 7195489 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6146. Min Range: -7.6146
Max Act: 7.0833. Min Act: -0.1700
Data Index: 662527 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6146. Min Range: -7.6146
Max Act: 7.0833. Min Act: -0.1700
Data Index: 6320211 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6146. Min Range: -7.6146
Max Act: 7.0521. Min Act: -0.1700
Data Index: 743932 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6146. Min Range: -7.6146
Max Act: 7.0833. Min Act: -0.1700
Data Index: 1766801 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6146. Min Range: -7.6146
Max Act: 7.0208. Min Act: -0.1700
Data Index: 1929477 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6146. Min Range: -7.6146
Max Act: 7.0208. Min Act: -0.1700
Data Index: 5855185 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6146. Min Range: -7.6146
Max Act: 6.9896. Min Act: -0.1700
Data Index: 1345763 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6146. Min Range: -7.6146
Max Act: 7.0208. Min Act: -0.1700
Data Index: 481981 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6146. Min Range: -7.6146
Max Act: 6.9896. Min Act: -0.1700
Data Index: 8380525 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6146. Min Range: -7.6146
Max Act: 6.9896. Min Act: -0.1700
Data Index: 2914459 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6146. Min Range: -7.6146
Max Act: 7.0208. Min Act: -0.1700
Data Index: 8317405 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19