Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1689 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6284. Min Range: -6.6284
Max Act: 6.6284. Min Act: -0.1700
Data Index: 3330846 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6284. Min Range: -6.6284
Max Act: 6.6284. Min Act: -0.1700
Data Index: 6454037 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6284. Min Range: -6.6284
Max Act: 6.5659. Min Act: -0.1700
Data Index: 1821789 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6284. Min Range: -6.6284
Max Act: 6.5346. Min Act: -0.1700
Data Index: 3994209 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6284. Min Range: -6.6284
Max Act: 6.3784. Min Act: -0.1700
Data Index: 1284098 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6284. Min Range: -6.6284
Max Act: 6.3471. Min Act: -0.1700
Data Index: 6771575 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6284. Min Range: -6.6284
Max Act: 6.3471. Min Act: -0.1700
Data Index: 3642234 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6284. Min Range: -6.6284
Max Act: 6.3159. Min Act: -0.1700
Data Index: 7332664 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6284. Min Range: -6.6284
Max Act: 6.3159. Min Act: -0.1700
Data Index: 1209604 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6284. Min Range: -6.6284
Max Act: 6.3159. Min Act: -0.1700
Data Index: 8507950 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6284. Min Range: -6.6284
Max Act: 6.2846. Min Act: -0.1700
Data Index: 5274342 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6284. Min Range: -6.6284
Max Act: 6.2846. Min Act: -0.1700
Data Index: 8385806 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6284. Min Range: -6.6284
Max Act: 6.2846. Min Act: -0.1700
Data Index: 1857327 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6284. Min Range: -6.6284
Max Act: 6.2221. Min Act: -0.1700
Data Index: 140667 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6284. Min Range: -6.6284
Max Act: 6.1909. Min Act: -0.1700
Data Index: 5966461 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6284. Min Range: -6.6284
Max Act: 6.1909. Min Act: -0.1700
Data Index: 6314186 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6284. Min Range: -6.6284
Max Act: 6.1909. Min Act: -0.1700
Data Index: 7254919 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6284. Min Range: -6.6284
Max Act: 6.1909. Min Act: -0.1700
Data Index: 5808248 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6284. Min Range: -6.6284
Max Act: 6.1284. Min Act: -0.1700
Data Index: 5324254 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6284. Min Range: -6.6284
Max Act: 6.1284. Min Act: -0.1700
Data Index: 3890527 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #19