Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5741 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7800. Min Range: -4.7800
Max Act: 4.7800. Min Act: -0.1700
Data Index: 2741952 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7800. Min Range: -4.7800
Max Act: 4.7175. Min Act: -0.1700
Data Index: 2144899 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7800. Min Range: -4.7800
Max Act: 4.6862. Min Act: -0.1700
Data Index: 165035 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7800. Min Range: -4.7800
Max Act: 4.6862. Min Act: -0.1700
Data Index: 458933 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7800. Min Range: -4.7800
Max Act: 4.6862. Min Act: -0.1700
Data Index: 431548 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7800. Min Range: -4.7800
Max Act: 4.6237. Min Act: -0.1700
Data Index: 5472036 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7800. Min Range: -4.7800
Max Act: 4.6550. Min Act: -0.1700
Data Index: 8771725 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7800. Min Range: -4.7800
Max Act: 4.6550. Min Act: -0.1700
Data Index: 2259922 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7800. Min Range: -4.7800
Max Act: 4.6550. Min Act: -0.1700
Data Index: 3046060 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7800. Min Range: -4.7800
Max Act: 4.6550. Min Act: -0.1700
Data Index: 4673694 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7800. Min Range: -4.7800
Max Act: 4.6237. Min Act: -0.1700
Data Index: 4641727 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7800. Min Range: -4.7800
Max Act: 4.5925. Min Act: -0.1700
Data Index: 4135735 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7800. Min Range: -4.7800
Max Act: 4.5925. Min Act: -0.1700
Data Index: 1781342 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7800. Min Range: -4.7800
Max Act: 4.5612. Min Act: -0.1700
Data Index: 7886630 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7800. Min Range: -4.7800
Max Act: 4.5925. Min Act: -0.1700
Data Index: 7478960 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7800. Min Range: -4.7800
Max Act: 4.5925. Min Act: -0.1700
Data Index: 7478959 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7800. Min Range: -4.7800
Max Act: 4.6237. Min Act: -0.1700
Data Index: 3069512 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7800. Min Range: -4.7800
Max Act: 4.5925. Min Act: -0.1700
Data Index: 2844724 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7800. Min Range: -4.7800
Max Act: 4.5300. Min Act: -0.1700
Data Index: 228779 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7800. Min Range: -4.7800
Max Act: 4.5300. Min Act: -0.1700
Data Index: 2259918 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #19