Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2797 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4028. Min Range: -6.4028
Max Act: 6.3715. Min Act: -0.1700
Data Index: 1195283 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4028. Min Range: -6.4028
Max Act: 6.4028. Min Act: -0.1700
Data Index: 2129233 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4028. Min Range: -6.4028
Max Act: 6.3715. Min Act: -0.1700
Data Index: 8558920 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4028. Min Range: -6.4028
Max Act: 6.2778. Min Act: -0.1700
Data Index: 875726 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4028. Min Range: -6.4028
Max Act: 6.2153. Min Act: -0.1700
Data Index: 969777 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4028. Min Range: -6.4028
Max Act: 6.1840. Min Act: -0.1700
Data Index: 3084670 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4028. Min Range: -6.4028
Max Act: 6.1528. Min Act: -0.1700
Data Index: 6597621 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4028. Min Range: -6.4028
Max Act: 6.1528. Min Act: -0.1700
Data Index: 4532607 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4028. Min Range: -6.4028
Max Act: 6.1528. Min Act: -0.1700
Data Index: 3823018 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4028. Min Range: -6.4028
Max Act: 6.0903. Min Act: -0.1700
Data Index: 4127085 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4028. Min Range: -6.4028
Max Act: 6.0903. Min Act: -0.1700
Data Index: 7672021 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4028. Min Range: -6.4028
Max Act: 6.0903. Min Act: -0.1700
Data Index: 340405 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4028. Min Range: -6.4028
Max Act: 6.0903. Min Act: -0.1700
Data Index: 1562950 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4028. Min Range: -6.4028
Max Act: 6.0903. Min Act: -0.1700
Data Index: 4457124 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4028. Min Range: -6.4028
Max Act: 6.0590. Min Act: -0.1700
Data Index: 4171732 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4028. Min Range: -6.4028
Max Act: 6.0590. Min Act: -0.1700
Data Index: 2566952 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4028. Min Range: -6.4028
Max Act: 6.0278. Min Act: -0.1700
Data Index: 3830569 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4028. Min Range: -6.4028
Max Act: 6.0278. Min Act: -0.1700
Data Index: 7974974 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4028. Min Range: -6.4028
Max Act: 6.0590. Min Act: -0.1700
Data Index: 314120 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4028. Min Range: -6.4028
Max Act: 5.9965. Min Act: -0.1700
Data Index: 3823391 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19