Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1850 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6843. Min Range: -4.6843
Max Act: 4.6531. Min Act: -0.1700
Data Index: 3609589 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6843. Min Range: -4.6843
Max Act: 4.6843. Min Act: -0.1700
Data Index: 2921187 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6843. Min Range: -4.6843
Max Act: 4.6531. Min Act: -0.1700
Data Index: 5370456 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6843. Min Range: -4.6843
Max Act: 4.6531. Min Act: -0.1700
Data Index: 8642369 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6843. Min Range: -4.6843
Max Act: 4.6218. Min Act: -0.1700
Data Index: 751105 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6843. Min Range: -4.6843
Max Act: 4.5906. Min Act: -0.1700
Data Index: 3944047 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6843. Min Range: -4.6843
Max Act: 4.6218. Min Act: -0.1700
Data Index: 8492094 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6843. Min Range: -4.6843
Max Act: 4.6218. Min Act: -0.1700
Data Index: 1046635 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6843. Min Range: -4.6843
Max Act: 4.5906. Min Act: -0.1700
Data Index: 1118083 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6843. Min Range: -4.6843
Max Act: 4.5906. Min Act: -0.1700
Data Index: 909161 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6843. Min Range: -4.6843
Max Act: 4.5906. Min Act: -0.1700
Data Index: 6608302 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6843. Min Range: -4.6843
Max Act: 4.5593. Min Act: -0.1700
Data Index: 661572 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6843. Min Range: -4.6843
Max Act: 4.5906. Min Act: -0.1700
Data Index: 131770 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6843. Min Range: -4.6843
Max Act: 4.5593. Min Act: -0.1700
Data Index: 1834909 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6843. Min Range: -4.6843
Max Act: 4.5593. Min Act: -0.1700
Data Index: 8750065 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6843. Min Range: -4.6843
Max Act: 4.5593. Min Act: -0.1700
Data Index: 8226967 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6843. Min Range: -4.6843
Max Act: 4.4968. Min Act: -0.1700
Data Index: 8134865 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6843. Min Range: -4.6843
Max Act: 4.5281. Min Act: -0.1700
Data Index: 7057678 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6843. Min Range: -4.6843
Max Act: 4.5281. Min Act: -0.1700
Data Index: 2710208 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6843. Min Range: -4.6843
Max Act: 4.4968. Min Act: -0.1700
Data Index: 5875193 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #19