Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3835 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7074. Min Range: -6.7074
Max Act: 6.7074. Min Act: -0.1700
Data Index: 3983206 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7074. Min Range: -6.7074
Max Act: 6.7074. Min Act: -0.1700
Data Index: 2403409 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7074. Min Range: -6.7074
Max Act: 6.6762. Min Act: -0.1700
Data Index: 5669588 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7074. Min Range: -6.7074
Max Act: 6.7074. Min Act: -0.1700
Data Index: 8679246 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7074. Min Range: -6.7074
Max Act: 6.6449. Min Act: -0.1700
Data Index: 26854 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7074. Min Range: -6.7074
Max Act: 6.6137. Min Act: -0.1700
Data Index: 1262704 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7074. Min Range: -6.7074
Max Act: 6.6137. Min Act: -0.1700
Data Index: 7180661 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7074. Min Range: -6.7074
Max Act: 6.6137. Min Act: -0.1700
Data Index: 2091659 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7074. Min Range: -6.7074
Max Act: 6.6137. Min Act: -0.1700
Data Index: 4230726 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7074. Min Range: -6.7074
Max Act: 6.6137. Min Act: -0.1700
Data Index: 7206866 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7074. Min Range: -6.7074
Max Act: 6.5824. Min Act: -0.1700
Data Index: 6058632 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7074. Min Range: -6.7074
Max Act: 6.5824. Min Act: -0.1700
Data Index: 2415340 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7074. Min Range: -6.7074
Max Act: 6.5512. Min Act: -0.1700
Data Index: 3313908 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7074. Min Range: -6.7074
Max Act: 6.5512. Min Act: -0.1700
Data Index: 6554697 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7074. Min Range: -6.7074
Max Act: 6.5512. Min Act: -0.1700
Data Index: 1005284 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7074. Min Range: -6.7074
Max Act: 6.5512. Min Act: -0.1700
Data Index: 5163236 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7074. Min Range: -6.7074
Max Act: 6.5512. Min Act: -0.1700
Data Index: 482183 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7074. Min Range: -6.7074
Max Act: 6.5199. Min Act: -0.1700
Data Index: 4947293 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7074. Min Range: -6.7074
Max Act: 6.4887. Min Act: -0.1700
Data Index: 4303062 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7074. Min Range: -6.7074
Max Act: 6.5199. Min Act: -0.1700
Data Index: 3467068 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #19