Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3246 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8913. Min Range: -4.8913
Max Act: 4.8913. Min Act: -0.1700
Data Index: 7910422 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8913. Min Range: -4.8913
Max Act: 4.7975. Min Act: -0.1700
Data Index: 8160122 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8913. Min Range: -4.8913
Max Act: 4.7350. Min Act: -0.1700
Data Index: 5657633 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8913. Min Range: -4.8913
Max Act: 4.6413. Min Act: -0.1700
Data Index: 4470525 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8913. Min Range: -4.8913
Max Act: 4.6413. Min Act: -0.1700
Data Index: 2747713 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8913. Min Range: -4.8913
Max Act: 4.6100. Min Act: -0.1700
Data Index: 7625926 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8913. Min Range: -4.8913
Max Act: 4.6100. Min Act: -0.1700
Data Index: 3968150 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8913. Min Range: -4.8913
Max Act: 4.5788. Min Act: -0.1700
Data Index: 3361165 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8913. Min Range: -4.8913
Max Act: 4.5788. Min Act: -0.1700
Data Index: 5948967 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8913. Min Range: -4.8913
Max Act: 4.5475. Min Act: -0.1700
Data Index: 285955 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8913. Min Range: -4.8913
Max Act: 4.5475. Min Act: -0.1700
Data Index: 4788227 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8913. Min Range: -4.8913
Max Act: 4.5475. Min Act: -0.1700
Data Index: 3576606 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8913. Min Range: -4.8913
Max Act: 4.5163. Min Act: -0.1700
Data Index: 285852 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8913. Min Range: -4.8913
Max Act: 4.4850. Min Act: -0.1700
Data Index: 2468282 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8913. Min Range: -4.8913
Max Act: 4.4850. Min Act: -0.1700
Data Index: 8137356 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8913. Min Range: -4.8913
Max Act: 4.4850. Min Act: -0.1700
Data Index: 3699515 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8913. Min Range: -4.8913
Max Act: 4.4850. Min Act: -0.1700
Data Index: 5349962 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8913. Min Range: -4.8913
Max Act: 4.5163. Min Act: -0.1700
Data Index: 1984270 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8913. Min Range: -4.8913
Max Act: 4.4850. Min Act: -0.1700
Data Index: 5941307 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8913. Min Range: -4.8913
Max Act: 4.4538. Min Act: -0.1700
Data Index: 1069836 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #19