Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5886 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7267. Min Range: -5.7267
Max Act: 5.7267. Min Act: -0.1700
Data Index: 8296655 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7267. Min Range: -5.7267
Max Act: 5.7267. Min Act: -0.1700
Data Index: 3959830 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7267. Min Range: -5.7267
Max Act: 5.6642. Min Act: -0.1700
Data Index: 5204276 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7267. Min Range: -5.7267
Max Act: 5.6642. Min Act: -0.1700
Data Index: 5905435 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7267. Min Range: -5.7267
Max Act: 5.6329. Min Act: -0.1700
Data Index: 6887425 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7267. Min Range: -5.7267
Max Act: 5.6642. Min Act: -0.1700
Data Index: 2466273 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7267. Min Range: -5.7267
Max Act: 5.6329. Min Act: -0.1700
Data Index: 7406420 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7267. Min Range: -5.7267
Max Act: 5.6017. Min Act: -0.1700
Data Index: 7744664 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7267. Min Range: -5.7267
Max Act: 5.6017. Min Act: -0.1700
Data Index: 3503777 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7267. Min Range: -5.7267
Max Act: 5.6017. Min Act: -0.1700
Data Index: 5133817 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7267. Min Range: -5.7267
Max Act: 5.6017. Min Act: -0.1700
Data Index: 6816317 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7267. Min Range: -5.7267
Max Act: 5.6017. Min Act: -0.1700
Data Index: 6535233 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7267. Min Range: -5.7267
Max Act: 5.6017. Min Act: -0.1700
Data Index: 5204272 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7267. Min Range: -5.7267
Max Act: 5.6017. Min Act: -0.1700
Data Index: 8815531 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7267. Min Range: -5.7267
Max Act: 5.5704. Min Act: -0.1700
Data Index: 3959831 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7267. Min Range: -5.7267
Max Act: 5.5704. Min Act: -0.1700
Data Index: 3817657 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7267. Min Range: -5.7267
Max Act: 5.6017. Min Act: -0.1700
Data Index: 3697298 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7267. Min Range: -5.7267
Max Act: 5.5704. Min Act: -0.1700
Data Index: 2210473 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7267. Min Range: -5.7267
Max Act: 5.5704. Min Act: -0.1700
Data Index: 5204271 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7267. Min Range: -5.7267
Max Act: 5.5704. Min Act: -0.1700
Data Index: 5885174 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19