Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3465 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8251. Min Range: -6.8251
Max Act: 6.8251. Min Act: -0.1700
Data Index: 2250732 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8251. Min Range: -6.8251
Max Act: 6.7001. Min Act: -0.1700
Data Index: 3805319 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8251. Min Range: -6.8251
Max Act: 6.4501. Min Act: -0.1700
Data Index: 166950 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8251. Min Range: -6.8251
Max Act: 6.4814. Min Act: -0.1700
Data Index: 7485735 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8251. Min Range: -6.8251
Max Act: 6.4189. Min Act: -0.1700
Data Index: 7710464 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8251. Min Range: -6.8251
Max Act: 6.4189. Min Act: -0.1700
Data Index: 1737170 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8251. Min Range: -6.8251
Max Act: 6.4189. Min Act: -0.1700
Data Index: 393621 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8251. Min Range: -6.8251
Max Act: 6.4189. Min Act: -0.1700
Data Index: 4562787 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8251. Min Range: -6.8251
Max Act: 6.3876. Min Act: -0.1700
Data Index: 176878 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8251. Min Range: -6.8251
Max Act: 6.3876. Min Act: -0.1700
Data Index: 2917559 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8251. Min Range: -6.8251
Max Act: 6.3876. Min Act: -0.1700
Data Index: 6286692 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8251. Min Range: -6.8251
Max Act: 6.3251. Min Act: -0.1700
Data Index: 3788193 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8251. Min Range: -6.8251
Max Act: 6.3251. Min Act: -0.1700
Data Index: 7005022 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8251. Min Range: -6.8251
Max Act: 6.2939. Min Act: -0.1700
Data Index: 5495923 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8251. Min Range: -6.8251
Max Act: 6.2939. Min Act: -0.1700
Data Index: 3676075 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8251. Min Range: -6.8251
Max Act: 6.2939. Min Act: -0.1700
Data Index: 429450 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8251. Min Range: -6.8251
Max Act: 6.2939. Min Act: -0.1700
Data Index: 5086550 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8251. Min Range: -6.8251
Max Act: 6.2626. Min Act: -0.1700
Data Index: 5438086 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8251. Min Range: -6.8251
Max Act: 6.2626. Min Act: -0.1700
Data Index: 6486776 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8251. Min Range: -6.8251
Max Act: 6.2939. Min Act: -0.1700
Data Index: 4822840 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #19