Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3214 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6863. Min Range: -5.6863
Max Act: 5.6863. Min Act: -0.1700
Data Index: 6070915 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6863. Min Range: -5.6863
Max Act: 5.6551. Min Act: -0.1700
Data Index: 3063586 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6863. Min Range: -5.6863
Max Act: 5.6238. Min Act: -0.1700
Data Index: 2946935 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6863. Min Range: -5.6863
Max Act: 5.5301. Min Act: -0.1700
Data Index: 5944763 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6863. Min Range: -5.6863
Max Act: 5.4988. Min Act: -0.1700
Data Index: 3596564 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6863. Min Range: -5.6863
Max Act: 5.4988. Min Act: -0.1700
Data Index: 8214112 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6863. Min Range: -5.6863
Max Act: 5.4676. Min Act: -0.1700
Data Index: 5238006 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6863. Min Range: -5.6863
Max Act: 5.4363. Min Act: -0.1700
Data Index: 5492428 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6863. Min Range: -5.6863
Max Act: 5.4051. Min Act: -0.1700
Data Index: 8425425 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6863. Min Range: -5.6863
Max Act: 5.4051. Min Act: -0.1700
Data Index: 5695005 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6863. Min Range: -5.6863
Max Act: 5.3738. Min Act: -0.1700
Data Index: 1069907 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6863. Min Range: -5.6863
Max Act: 5.3738. Min Act: -0.1700
Data Index: 4737822 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6863. Min Range: -5.6863
Max Act: 5.3738. Min Act: -0.1700
Data Index: 2808144 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6863. Min Range: -5.6863
Max Act: 5.4051. Min Act: -0.1700
Data Index: 1885432 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6863. Min Range: -5.6863
Max Act: 5.3738. Min Act: -0.1700
Data Index: 3897713 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6863. Min Range: -5.6863
Max Act: 5.3426. Min Act: -0.1700
Data Index: 8771935 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6863. Min Range: -5.6863
Max Act: 5.3426. Min Act: -0.1700
Data Index: 5474317 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6863. Min Range: -5.6863
Max Act: 5.3113. Min Act: -0.1700
Data Index: 1282272 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6863. Min Range: -5.6863
Max Act: 5.2801. Min Act: -0.1700
Data Index: 600707 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6863. Min Range: -5.6863
Max Act: 5.2801. Min Act: -0.1700
Data Index: 8210043 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #19