Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2917 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0995. Min Range: -5.0995
Max Act: 5.0995. Min Act: -0.1700
Data Index: 3629031 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0995. Min Range: -5.0995
Max Act: 5.0058. Min Act: -0.1700
Data Index: 2358686 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0995. Min Range: -5.0995
Max Act: 4.9745. Min Act: -0.1700
Data Index: 6415648 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0995. Min Range: -5.0995
Max Act: 4.8808. Min Act: -0.1700
Data Index: 167367 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0995. Min Range: -5.0995
Max Act: 4.8808. Min Act: -0.1700
Data Index: 2309911 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0995. Min Range: -5.0995
Max Act: 4.8495. Min Act: -0.1700
Data Index: 2382673 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0995. Min Range: -5.0995
Max Act: 4.8495. Min Act: -0.1700
Data Index: 4379962 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0995. Min Range: -5.0995
Max Act: 4.8495. Min Act: -0.1700
Data Index: 114809 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0995. Min Range: -5.0995
Max Act: 4.8183. Min Act: -0.1700
Data Index: 8797296 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0995. Min Range: -5.0995
Max Act: 4.7870. Min Act: -0.1700
Data Index: 1212799 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0995. Min Range: -5.0995
Max Act: 4.8183. Min Act: -0.1700
Data Index: 2670125 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0995. Min Range: -5.0995
Max Act: 4.7870. Min Act: -0.1700
Data Index: 1783689 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0995. Min Range: -5.0995
Max Act: 4.8183. Min Act: -0.1700
Data Index: 6869057 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0995. Min Range: -5.0995
Max Act: 4.7870. Min Act: -0.1700
Data Index: 8754842 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0995. Min Range: -5.0995
Max Act: 4.7558. Min Act: -0.1700
Data Index: 8686887 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0995. Min Range: -5.0995
Max Act: 4.7870. Min Act: -0.1700
Data Index: 4802530 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0995. Min Range: -5.0995
Max Act: 4.7870. Min Act: -0.1700
Data Index: 2671821 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0995. Min Range: -5.0995
Max Act: 4.7870. Min Act: -0.1700
Data Index: 8452495 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0995. Min Range: -5.0995
Max Act: 4.7870. Min Act: -0.1700
Data Index: 7814078 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0995. Min Range: -5.0995
Max Act: 4.7870. Min Act: -0.1700
Data Index: 6137663 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19