Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2672 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9176. Min Range: -5.9176
Max Act: 5.9176. Min Act: -0.1700
Data Index: 8446512 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9176. Min Range: -5.9176
Max Act: 5.9176. Min Act: -0.1700
Data Index: 5669773 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9176. Min Range: -5.9176
Max Act: 5.5738. Min Act: -0.1700
Data Index: 1695639 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9176. Min Range: -5.9176
Max Act: 5.4488. Min Act: -0.1700
Data Index: 1750332 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9176. Min Range: -5.9176
Max Act: 5.4176. Min Act: -0.1700
Data Index: 1917192 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9176. Min Range: -5.9176
Max Act: 5.3863. Min Act: -0.1700
Data Index: 4583628 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9176. Min Range: -5.9176
Max Act: 5.3863. Min Act: -0.1700
Data Index: 7374087 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9176. Min Range: -5.9176
Max Act: 5.3863. Min Act: -0.1700
Data Index: 5903945 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9176. Min Range: -5.9176
Max Act: 5.3551. Min Act: -0.1700
Data Index: 8683151 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9176. Min Range: -5.9176
Max Act: 5.3551. Min Act: -0.1700
Data Index: 3670758 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9176. Min Range: -5.9176
Max Act: 5.2926. Min Act: -0.1700
Data Index: 6644481 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9176. Min Range: -5.9176
Max Act: 5.2613. Min Act: -0.1700
Data Index: 4399174 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9176. Min Range: -5.9176
Max Act: 5.2926. Min Act: -0.1700
Data Index: 1323251 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9176. Min Range: -5.9176
Max Act: 5.1988. Min Act: -0.1700
Data Index: 4539868 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9176. Min Range: -5.9176
Max Act: 5.1988. Min Act: -0.1700
Data Index: 6944213 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9176. Min Range: -5.9176
Max Act: 5.1988. Min Act: -0.1700
Data Index: 4954224 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9176. Min Range: -5.9176
Max Act: 5.1988. Min Act: -0.1700
Data Index: 8170923 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9176. Min Range: -5.9176
Max Act: 5.1676. Min Act: -0.1700
Data Index: 20380 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9176. Min Range: -5.9176
Max Act: 5.1676. Min Act: -0.1700
Data Index: 3649352 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9176. Min Range: -5.9176
Max Act: 5.1676. Min Act: -0.1700
Data Index: 3264499 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #19