Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 851 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5973. Min Range: -8.5973
Max Act: 8.5973. Min Act: -0.1700
Data Index: 8270883 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5973. Min Range: -8.5973
Max Act: 8.5348. Min Act: -0.1700
Data Index: 5503713 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5973. Min Range: -8.5973
Max Act: 8.0035. Min Act: -0.1700
Data Index: 4757609 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5973. Min Range: -8.5973
Max Act: 7.9098. Min Act: -0.1700
Data Index: 2916608 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5973. Min Range: -8.5973
Max Act: 7.8785. Min Act: -0.1700
Data Index: 7278262 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5973. Min Range: -8.5973
Max Act: 7.8473. Min Act: -0.1700
Data Index: 8464145 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5973. Min Range: -8.5973
Max Act: 7.7848. Min Act: -0.1700
Data Index: 1891876 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5973. Min Range: -8.5973
Max Act: 7.7535. Min Act: -0.1700
Data Index: 5852953 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5973. Min Range: -8.5973
Max Act: 7.7535. Min Act: -0.1700
Data Index: 2834327 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5973. Min Range: -8.5973
Max Act: 7.6910. Min Act: -0.1700
Data Index: 1959670 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5973. Min Range: -8.5973
Max Act: 7.6598. Min Act: -0.1700
Data Index: 3033227 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5973. Min Range: -8.5973
Max Act: 7.5973. Min Act: -0.1700
Data Index: 7439815 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5973. Min Range: -8.5973
Max Act: 7.6285. Min Act: -0.1700
Data Index: 2297799 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5973. Min Range: -8.5973
Max Act: 7.5973. Min Act: -0.1700
Data Index: 4716735 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5973. Min Range: -8.5973
Max Act: 7.5973. Min Act: -0.1700
Data Index: 7569174 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5973. Min Range: -8.5973
Max Act: 7.5973. Min Act: -0.1700
Data Index: 4103420 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5973. Min Range: -8.5973
Max Act: 7.5035. Min Act: -0.1700
Data Index: 1825666 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5973. Min Range: -8.5973
Max Act: 7.5035. Min Act: -0.1700
Data Index: 3455462 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5973. Min Range: -8.5973
Max Act: 7.5035. Min Act: -0.1700
Data Index: 2893465 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5973. Min Range: -8.5973
Max Act: 7.5348. Min Act: -0.1700
Data Index: 6445666 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #19