Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1026 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7746. Min Range: -6.7746
Max Act: 6.7746. Min Act: -0.1700
Data Index: 5339615 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7746. Min Range: -6.7746
Max Act: 6.7121. Min Act: -0.1700
Data Index: 528657 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7746. Min Range: -6.7746
Max Act: 6.6496. Min Act: -0.1700
Data Index: 7715583 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7746. Min Range: -6.7746
Max Act: 6.5871. Min Act: -0.1700
Data Index: 8363352 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7746. Min Range: -6.7746
Max Act: 6.6496. Min Act: -0.1700
Data Index: 2660769 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7746. Min Range: -6.7746
Max Act: 6.5871. Min Act: -0.1700
Data Index: 7372763 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7746. Min Range: -6.7746
Max Act: 6.5871. Min Act: -0.1700
Data Index: 680144 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7746. Min Range: -6.7746
Max Act: 6.5246. Min Act: -0.1700
Data Index: 6164154 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7746. Min Range: -6.7746
Max Act: 6.5246. Min Act: -0.1700
Data Index: 1252610 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7746. Min Range: -6.7746
Max Act: 6.5246. Min Act: -0.1700
Data Index: 302004 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7746. Min Range: -6.7746
Max Act: 6.5246. Min Act: -0.1700
Data Index: 5314066 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7746. Min Range: -6.7746
Max Act: 6.5246. Min Act: -0.1700
Data Index: 325230 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7746. Min Range: -6.7746
Max Act: 6.5246. Min Act: -0.1700
Data Index: 930274 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7746. Min Range: -6.7746
Max Act: 6.4621. Min Act: -0.1700
Data Index: 6535497 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7746. Min Range: -6.7746
Max Act: 6.5246. Min Act: -0.1700
Data Index: 227627 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7746. Min Range: -6.7746
Max Act: 6.4621. Min Act: -0.1700
Data Index: 1214736 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7746. Min Range: -6.7746
Max Act: 6.4621. Min Act: -0.1700
Data Index: 4649401 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7746. Min Range: -6.7746
Max Act: 6.4621. Min Act: -0.1700
Data Index: 3310973 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7746. Min Range: -6.7746
Max Act: 6.4621. Min Act: -0.1700
Data Index: 185239 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7746. Min Range: -6.7746
Max Act: 6.4621. Min Act: -0.1700
Data Index: 2154818 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #19