Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 794 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9664. Min Range: -6.9664
Max Act: 6.9664. Min Act: -0.1700
Data Index: 2007528 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9664. Min Range: -6.9664
Max Act: 6.7789. Min Act: -0.1700
Data Index: 6551582 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9664. Min Range: -6.9664
Max Act: 6.8101. Min Act: -0.1700
Data Index: 2308056 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9664. Min Range: -6.9664
Max Act: 6.7789. Min Act: -0.1700
Data Index: 6632065 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9664. Min Range: -6.9664
Max Act: 6.7476. Min Act: -0.1700
Data Index: 4265173 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9664. Min Range: -6.9664
Max Act: 6.6851. Min Act: -0.1700
Data Index: 8762760 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9664. Min Range: -6.9664
Max Act: 6.7164. Min Act: -0.1700
Data Index: 4244168 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9664. Min Range: -6.9664
Max Act: 6.6851. Min Act: -0.1700
Data Index: 3760923 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9664. Min Range: -6.9664
Max Act: 6.6539. Min Act: -0.1700
Data Index: 8355395 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9664. Min Range: -6.9664
Max Act: 6.6226. Min Act: -0.1700
Data Index: 10622 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9664. Min Range: -6.9664
Max Act: 6.5914. Min Act: -0.1700
Data Index: 559582 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9664. Min Range: -6.9664
Max Act: 6.5914. Min Act: -0.1700
Data Index: 6816576 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9664. Min Range: -6.9664
Max Act: 6.5914. Min Act: -0.1700
Data Index: 2812969 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9664. Min Range: -6.9664
Max Act: 6.5601. Min Act: -0.1700
Data Index: 3928221 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9664. Min Range: -6.9664
Max Act: 6.5601. Min Act: -0.1700
Data Index: 1638063 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9664. Min Range: -6.9664
Max Act: 6.5289. Min Act: -0.1700
Data Index: 3392865 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9664. Min Range: -6.9664
Max Act: 6.5289. Min Act: -0.1700
Data Index: 3305125 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9664. Min Range: -6.9664
Max Act: 6.5289. Min Act: -0.1700
Data Index: 4777210 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9664. Min Range: -6.9664
Max Act: 6.5289. Min Act: -0.1700
Data Index: 6334748 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9664. Min Range: -6.9664
Max Act: 6.5289. Min Act: -0.1700
Data Index: 2594002 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19