Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4680 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0035. Min Range: -8.0035
Max Act: 8.0035. Min Act: -0.1700
Data Index: 5710964 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0035. Min Range: -8.0035
Max Act: 8.0035. Min Act: -0.1700
Data Index: 258567 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0035. Min Range: -8.0035
Max Act: 7.8785. Min Act: -0.1700
Data Index: 6758068 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0035. Min Range: -8.0035
Max Act: 7.8785. Min Act: -0.1700
Data Index: 3896885 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0035. Min Range: -8.0035
Max Act: 7.8160. Min Act: -0.1700
Data Index: 5263111 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0035. Min Range: -8.0035
Max Act: 7.6910. Min Act: -0.1700
Data Index: 4949491 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0035. Min Range: -8.0035
Max Act: 7.6910. Min Act: -0.1700
Data Index: 4843196 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0035. Min Range: -8.0035
Max Act: 7.7535. Min Act: -0.1700
Data Index: 5707930 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0035. Min Range: -8.0035
Max Act: 7.6910. Min Act: -0.1700
Data Index: 2663920 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0035. Min Range: -8.0035
Max Act: 7.6285. Min Act: -0.1700
Data Index: 2421769 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0035. Min Range: -8.0035
Max Act: 7.6285. Min Act: -0.1700
Data Index: 5245924 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0035. Min Range: -8.0035
Max Act: 7.5660. Min Act: -0.1700
Data Index: 3160735 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0035. Min Range: -8.0035
Max Act: 7.5660. Min Act: -0.1700
Data Index: 4089034 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0035. Min Range: -8.0035
Max Act: 7.5035. Min Act: -0.1700
Data Index: 4234393 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0035. Min Range: -8.0035
Max Act: 7.5660. Min Act: -0.1700
Data Index: 7569797 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0035. Min Range: -8.0035
Max Act: 7.5660. Min Act: -0.1700
Data Index: 3697174 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0035. Min Range: -8.0035
Max Act: 7.5035. Min Act: -0.1700
Data Index: 1054373 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0035. Min Range: -8.0035
Max Act: 7.5035. Min Act: -0.1700
Data Index: 7951203 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0035. Min Range: -8.0035
Max Act: 7.5035. Min Act: -0.1700
Data Index: 5119888 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0035. Min Range: -8.0035
Max Act: 7.5035. Min Act: -0.1700
Data Index: 5291271 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #19