Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3647 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1955. Min Range: -8.1955
Max Act: 8.1955. Min Act: -0.1700
Data Index: 1115112 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1955. Min Range: -8.1955
Max Act: 8.0705. Min Act: -0.1700
Data Index: 3703541 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1955. Min Range: -8.1955
Max Act: 8.0080. Min Act: -0.1700
Data Index: 1313544 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1955. Min Range: -8.1955
Max Act: 8.0080. Min Act: -0.1700
Data Index: 5822494 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1955. Min Range: -8.1955
Max Act: 7.8830. Min Act: -0.1700
Data Index: 6208241 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1955. Min Range: -8.1955
Max Act: 7.8830. Min Act: -0.1700
Data Index: 1240725 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1955. Min Range: -8.1955
Max Act: 7.8205. Min Act: -0.1700
Data Index: 359682 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1955. Min Range: -8.1955
Max Act: 7.8205. Min Act: -0.1700
Data Index: 8128071 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1955. Min Range: -8.1955
Max Act: 7.7580. Min Act: -0.1700
Data Index: 3687635 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1955. Min Range: -8.1955
Max Act: 7.7580. Min Act: -0.1700
Data Index: 6533759 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1955. Min Range: -8.1955
Max Act: 7.6955. Min Act: -0.1700
Data Index: 6232987 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1955. Min Range: -8.1955
Max Act: 7.6955. Min Act: -0.1700
Data Index: 479480 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1955. Min Range: -8.1955
Max Act: 7.6955. Min Act: -0.1700
Data Index: 2926622 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1955. Min Range: -8.1955
Max Act: 7.6017. Min Act: -0.1700
Data Index: 20780 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1955. Min Range: -8.1955
Max Act: 7.5705. Min Act: -0.1700
Data Index: 181250 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1955. Min Range: -8.1955
Max Act: 7.5705. Min Act: -0.1700
Data Index: 3864062 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1955. Min Range: -8.1955
Max Act: 7.5392. Min Act: -0.1700
Data Index: 3720358 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1955. Min Range: -8.1955
Max Act: 7.4767. Min Act: -0.1700
Data Index: 7691996 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1955. Min Range: -8.1955
Max Act: 7.5392. Min Act: -0.1700
Data Index: 6263946 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1955. Min Range: -8.1955
Max Act: 7.5080. Min Act: -0.1700
Data Index: 8236756 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #19