Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1908 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4641. Min Range: -7.4641
Max Act: 7.4641. Min Act: -0.1700
Data Index: 3682454 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4641. Min Range: -7.4641
Max Act: 7.2766. Min Act: -0.1700
Data Index: 5590881 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4641. Min Range: -7.4641
Max Act: 7.2141. Min Act: -0.1700
Data Index: 5277048 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4641. Min Range: -7.4641
Max Act: 7.2453. Min Act: -0.1700
Data Index: 6105387 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4641. Min Range: -7.4641
Max Act: 7.1828. Min Act: -0.1700
Data Index: 899603 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4641. Min Range: -7.4641
Max Act: 7.1828. Min Act: -0.1700
Data Index: 6860391 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4641. Min Range: -7.4641
Max Act: 7.1516. Min Act: -0.1700
Data Index: 7483984 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4641. Min Range: -7.4641
Max Act: 7.1516. Min Act: -0.1700
Data Index: 2201002 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4641. Min Range: -7.4641
Max Act: 7.0891. Min Act: -0.1700
Data Index: 7160234 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4641. Min Range: -7.4641
Max Act: 7.0891. Min Act: -0.1700
Data Index: 4715770 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4641. Min Range: -7.4641
Max Act: 7.1203. Min Act: -0.1700
Data Index: 908091 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4641. Min Range: -7.4641
Max Act: 7.0266. Min Act: -0.1700
Data Index: 7996447 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4641. Min Range: -7.4641
Max Act: 7.0266. Min Act: -0.1700
Data Index: 8217884 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4641. Min Range: -7.4641
Max Act: 7.0266. Min Act: -0.1700
Data Index: 7891548 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4641. Min Range: -7.4641
Max Act: 6.9953. Min Act: -0.1700
Data Index: 6482517 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4641. Min Range: -7.4641
Max Act: 6.9953. Min Act: -0.1700
Data Index: 6294045 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4641. Min Range: -7.4641
Max Act: 6.9641. Min Act: -0.1700
Data Index: 8265013 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4641. Min Range: -7.4641
Max Act: 7.0266. Min Act: -0.1700
Data Index: 4985748 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4641. Min Range: -7.4641
Max Act: 7.0266. Min Act: -0.1700
Data Index: 7176562 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4641. Min Range: -7.4641
Max Act: 6.9328. Min Act: -0.1700
Data Index: 503407 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19