Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 282 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7207. Min Range: -5.7207
Max Act: 5.7207. Min Act: -0.1700
Data Index: 7036343 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7207. Min Range: -5.7207
Max Act: 5.5645. Min Act: -0.1700
Data Index: 1906479 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7207. Min Range: -5.7207
Max Act: 5.5332. Min Act: -0.1700
Data Index: 5897999 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7207. Min Range: -5.7207
Max Act: 5.5020. Min Act: -0.1700
Data Index: 2831163 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7207. Min Range: -5.7207
Max Act: 5.4707. Min Act: -0.1700
Data Index: 2479170 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7207. Min Range: -5.7207
Max Act: 5.4707. Min Act: -0.1700
Data Index: 4460955 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7207. Min Range: -5.7207
Max Act: 5.4707. Min Act: -0.1700
Data Index: 545519 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7207. Min Range: -5.7207
Max Act: 5.5020. Min Act: -0.1700
Data Index: 8674623 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7207. Min Range: -5.7207
Max Act: 5.4707. Min Act: -0.1700
Data Index: 7741112 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7207. Min Range: -5.7207
Max Act: 5.4707. Min Act: -0.1700
Data Index: 1908120 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7207. Min Range: -5.7207
Max Act: 5.4707. Min Act: -0.1700
Data Index: 2180655 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7207. Min Range: -5.7207
Max Act: 5.4707. Min Act: -0.1700
Data Index: 7439524 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7207. Min Range: -5.7207
Max Act: 5.4395. Min Act: -0.1700
Data Index: 7554041 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7207. Min Range: -5.7207
Max Act: 5.4082. Min Act: -0.1700
Data Index: 5289896 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7207. Min Range: -5.7207
Max Act: 5.4082. Min Act: -0.1700
Data Index: 7799813 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7207. Min Range: -5.7207
Max Act: 5.3770. Min Act: -0.1700
Data Index: 5986818 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7207. Min Range: -5.7207
Max Act: 5.3770. Min Act: -0.1700
Data Index: 4627625 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7207. Min Range: -5.7207
Max Act: 5.3770. Min Act: -0.1700
Data Index: 5913652 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7207. Min Range: -5.7207
Max Act: 5.3457. Min Act: -0.1700
Data Index: 1322917 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7207. Min Range: -5.7207
Max Act: 5.3145. Min Act: -0.1700
Data Index: 5088580 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19