Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1131 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.8869. Min Act: -0.1700
Data Index: 5113978 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.7306. Min Act: -0.1700
Data Index: 5113981 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.5119. Min Act: -0.1681
Data Index: 1817876 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.5119. Min Act: -0.1624
Data Index: 1817871 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.4494. Min Act: -0.1573
Data Index: 1817880 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.3244. Min Act: -0.1700
Data Index: 4811852 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.3244. Min Act: -0.1700
Data Index: 8363835 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.2931. Min Act: -0.1700
Data Index: 2825466 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.2931. Min Act: -0.1700
Data Index: 5113980 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.2619. Min Act: -0.1700
Data Index: 6434497 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.2931. Min Act: -0.1696
Data Index: 4811854 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.2619. Min Act: -0.1700
Data Index: 5113977 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.2306. Min Act: -0.1700
Data Index: 8363823 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.1994. Min Act: -0.1700
Data Index: 2825465 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.1056. Min Act: -0.1700
Data Index: 2825459 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.1056. Min Act: -0.1700
Data Index: 8363824 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.1056. Min Act: -0.1454
Data Index: 1817868 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.0744. Min Act: -0.1539
Data Index: 1817886 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.1056. Min Act: -0.1681
Data Index: 1817872 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.0744. Min Act: -0.1697
Data Index: 1817878 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #19