Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4491 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5719. Min Range: -6.5719
Max Act: 6.5406. Min Act: -0.1700
Data Index: 6162304 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5719. Min Range: -6.5719
Max Act: 6.5719. Min Act: -0.1700
Data Index: 3341008 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5719. Min Range: -6.5719
Max Act: 6.5406. Min Act: -0.1700
Data Index: 7413823 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5719. Min Range: -6.5719
Max Act: 6.5406. Min Act: -0.1700
Data Index: 3921378 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5719. Min Range: -6.5719
Max Act: 6.5094. Min Act: -0.1700
Data Index: 2677379 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5719. Min Range: -6.5719
Max Act: 6.4781. Min Act: -0.1700
Data Index: 4338379 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5719. Min Range: -6.5719
Max Act: 6.4469. Min Act: -0.1700
Data Index: 6856358 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5719. Min Range: -6.5719
Max Act: 6.3844. Min Act: -0.1700
Data Index: 6159059 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5719. Min Range: -6.5719
Max Act: 6.3844. Min Act: -0.1700
Data Index: 3339588 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5719. Min Range: -6.5719
Max Act: 6.3219. Min Act: -0.1700
Data Index: 6060738 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5719. Min Range: -6.5719
Max Act: 6.2906. Min Act: -0.1700
Data Index: 6275706 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5719. Min Range: -6.5719
Max Act: 6.2281. Min Act: -0.1700
Data Index: 255022 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5719. Min Range: -6.5719
Max Act: 6.2281. Min Act: -0.1700
Data Index: 576694 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5719. Min Range: -6.5719
Max Act: 6.2594. Min Act: -0.1700
Data Index: 5119596 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5719. Min Range: -6.5719
Max Act: 6.2281. Min Act: -0.1700
Data Index: 624935 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5719. Min Range: -6.5719
Max Act: 6.1969. Min Act: -0.1700
Data Index: 4147516 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5719. Min Range: -6.5719
Max Act: 6.1969. Min Act: -0.1700
Data Index: 6536153 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5719. Min Range: -6.5719
Max Act: 6.2281. Min Act: -0.1700
Data Index: 610223 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5719. Min Range: -6.5719
Max Act: 6.1969. Min Act: -0.1700
Data Index: 3687908 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5719. Min Range: -6.5719
Max Act: 6.1969. Min Act: -0.1700
Data Index: 2259600 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #19