Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3164 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0265. Min Range: -5.0265
Max Act: 5.0265. Min Act: -0.1700
Data Index: 5825321 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0265. Min Range: -5.0265
Max Act: 4.9640. Min Act: -0.1700
Data Index: 59226 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0265. Min Range: -5.0265
Max Act: 4.9640. Min Act: -0.1700
Data Index: 2459860 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0265. Min Range: -5.0265
Max Act: 4.9015. Min Act: -0.1700
Data Index: 136622 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0265. Min Range: -5.0265
Max Act: 4.9015. Min Act: -0.1700
Data Index: 244684 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0265. Min Range: -5.0265
Max Act: 4.9015. Min Act: -0.1700
Data Index: 7530981 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0265. Min Range: -5.0265
Max Act: 4.8703. Min Act: -0.1700
Data Index: 6357751 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0265. Min Range: -5.0265
Max Act: 4.8390. Min Act: -0.1700
Data Index: 2587800 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0265. Min Range: -5.0265
Max Act: 4.8390. Min Act: -0.1700
Data Index: 4902470 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0265. Min Range: -5.0265
Max Act: 4.8390. Min Act: -0.1700
Data Index: 1694515 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0265. Min Range: -5.0265
Max Act: 4.8078. Min Act: -0.1700
Data Index: 5923623 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0265. Min Range: -5.0265
Max Act: 4.8078. Min Act: -0.1700
Data Index: 5923625 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0265. Min Range: -5.0265
Max Act: 4.8078. Min Act: -0.1700
Data Index: 366257 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0265. Min Range: -5.0265
Max Act: 4.8078. Min Act: -0.1700
Data Index: 6949849 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0265. Min Range: -5.0265
Max Act: 4.8078. Min Act: -0.1700
Data Index: 6553123 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0265. Min Range: -5.0265
Max Act: 4.7765. Min Act: -0.1700
Data Index: 1725818 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0265. Min Range: -5.0265
Max Act: 4.7765. Min Act: -0.1700
Data Index: 4842296 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0265. Min Range: -5.0265
Max Act: 4.7765. Min Act: -0.1700
Data Index: 8524404 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0265. Min Range: -5.0265
Max Act: 4.7453. Min Act: -0.1700
Data Index: 3277708 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0265. Min Range: -5.0265
Max Act: 4.7453. Min Act: -0.1700
Data Index: 5876090 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #19