Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3939 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9156. Min Range: -6.9156
Max Act: 6.9156. Min Act: -0.1700
Data Index: 2143267 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9156. Min Range: -6.9156
Max Act: 6.6344. Min Act: -0.1700
Data Index: 5375699 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9156. Min Range: -6.9156
Max Act: 6.5094. Min Act: -0.1700
Data Index: 7869386 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9156. Min Range: -6.9156
Max Act: 6.5094. Min Act: -0.1700
Data Index: 1955863 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9156. Min Range: -6.9156
Max Act: 6.4781. Min Act: -0.1700
Data Index: 8741466 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9156. Min Range: -6.9156
Max Act: 6.4781. Min Act: -0.1700
Data Index: 248537 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9156. Min Range: -6.9156
Max Act: 6.4156. Min Act: -0.1700
Data Index: 632589 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9156. Min Range: -6.9156
Max Act: 6.4156. Min Act: -0.1700
Data Index: 3157737 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9156. Min Range: -6.9156
Max Act: 6.3844. Min Act: -0.1700
Data Index: 4634948 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9156. Min Range: -6.9156
Max Act: 6.3531. Min Act: -0.1700
Data Index: 4021866 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9156. Min Range: -6.9156
Max Act: 6.3531. Min Act: -0.1700
Data Index: 5724289 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9156. Min Range: -6.9156
Max Act: 6.3219. Min Act: -0.1700
Data Index: 3240974 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9156. Min Range: -6.9156
Max Act: 6.3219. Min Act: -0.1700
Data Index: 241026 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9156. Min Range: -6.9156
Max Act: 6.2906. Min Act: -0.1700
Data Index: 4301303 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9156. Min Range: -6.9156
Max Act: 6.2594. Min Act: -0.1700
Data Index: 5875139 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9156. Min Range: -6.9156
Max Act: 6.2594. Min Act: -0.1700
Data Index: 6056595 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9156. Min Range: -6.9156
Max Act: 6.2906. Min Act: -0.1700
Data Index: 7337561 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9156. Min Range: -6.9156
Max Act: 6.2281. Min Act: -0.1700
Data Index: 340770 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9156. Min Range: -6.9156
Max Act: 6.2281. Min Act: -0.1700
Data Index: 1900370 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9156. Min Range: -6.9156
Max Act: 6.1969. Min Act: -0.1700
Data Index: 7681518 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #19