Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3715 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1715. Min Range: -7.1715
Max Act: 7.1715. Min Act: -0.1700
Data Index: 4748451 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1715. Min Range: -7.1715
Max Act: 7.0777. Min Act: -0.1700
Data Index: 2357068 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1715. Min Range: -7.1715
Max Act: 7.0152. Min Act: -0.1700
Data Index: 105049 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1715. Min Range: -7.1715
Max Act: 6.9527. Min Act: -0.1700
Data Index: 2183147 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1715. Min Range: -7.1715
Max Act: 6.8902. Min Act: -0.1700
Data Index: 195033 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1715. Min Range: -7.1715
Max Act: 6.8902. Min Act: -0.1700
Data Index: 3733239 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1715. Min Range: -7.1715
Max Act: 6.8277. Min Act: -0.1700
Data Index: 2589570 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1715. Min Range: -7.1715
Max Act: 6.8277. Min Act: -0.1700
Data Index: 594211 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1715. Min Range: -7.1715
Max Act: 6.8277. Min Act: -0.1700
Data Index: 628355 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1715. Min Range: -7.1715
Max Act: 6.7965. Min Act: -0.1700
Data Index: 5979001 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1715. Min Range: -7.1715
Max Act: 6.7652. Min Act: -0.1700
Data Index: 5044990 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1715. Min Range: -7.1715
Max Act: 6.7340. Min Act: -0.1700
Data Index: 1752550 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1715. Min Range: -7.1715
Max Act: 6.7340. Min Act: -0.1700
Data Index: 6290890 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1715. Min Range: -7.1715
Max Act: 6.7340. Min Act: -0.1700
Data Index: 8054799 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1715. Min Range: -7.1715
Max Act: 6.7652. Min Act: -0.1700
Data Index: 1032767 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1715. Min Range: -7.1715
Max Act: 6.7027. Min Act: -0.1700
Data Index: 3555602 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1715. Min Range: -7.1715
Max Act: 6.7027. Min Act: -0.1700
Data Index: 4647417 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1715. Min Range: -7.1715
Max Act: 6.7027. Min Act: -0.1700
Data Index: 6087176 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1715. Min Range: -7.1715
Max Act: 6.6715. Min Act: -0.1700
Data Index: 2249714 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1715. Min Range: -7.1715
Max Act: 6.6090. Min Act: -0.1700
Data Index: 6546797 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #19