Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5151 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1398. Min Range: -6.1398
Max Act: 6.1398. Min Act: -0.1700
Data Index: 5879193 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1398. Min Range: -6.1398
Max Act: 5.9523. Min Act: -0.1700
Data Index: 1741804 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1398. Min Range: -6.1398
Max Act: 5.9523. Min Act: -0.1700
Data Index: 5368865 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1398. Min Range: -6.1398
Max Act: 5.9523. Min Act: -0.1700
Data Index: 2246874 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1398. Min Range: -6.1398
Max Act: 5.9210. Min Act: -0.1700
Data Index: 2246875 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1398. Min Range: -6.1398
Max Act: 5.9210. Min Act: -0.1700
Data Index: 64341 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1398. Min Range: -6.1398
Max Act: 5.9210. Min Act: -0.1700
Data Index: 2591555 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1398. Min Range: -6.1398
Max Act: 5.9210. Min Act: -0.1700
Data Index: 1544049 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1398. Min Range: -6.1398
Max Act: 5.9210. Min Act: -0.1700
Data Index: 893113 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1398. Min Range: -6.1398
Max Act: 5.8898. Min Act: -0.1700
Data Index: 2989315 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1398. Min Range: -6.1398
Max Act: 5.8898. Min Act: -0.1700
Data Index: 3824204 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1398. Min Range: -6.1398
Max Act: 5.8898. Min Act: -0.1700
Data Index: 5830133 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1398. Min Range: -6.1398
Max Act: 5.8898. Min Act: -0.1700
Data Index: 3903763 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1398. Min Range: -6.1398
Max Act: 5.8585. Min Act: -0.1700
Data Index: 1346551 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1398. Min Range: -6.1398
Max Act: 5.8585. Min Act: -0.1700
Data Index: 2647159 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1398. Min Range: -6.1398
Max Act: 5.8585. Min Act: -0.1700
Data Index: 6379259 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1398. Min Range: -6.1398
Max Act: 5.8585. Min Act: -0.1700
Data Index: 848938 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1398. Min Range: -6.1398
Max Act: 5.8585. Min Act: -0.1700
Data Index: 3318091 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1398. Min Range: -6.1398
Max Act: 5.8273. Min Act: -0.1700
Data Index: 4731753 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1398. Min Range: -6.1398
Max Act: 5.8273. Min Act: -0.1700
Data Index: 5040904 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #19