Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3572 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.8550. Min Range: -12.8550
Max Act: 12.8550. Min Act: -0.1700
Data Index: 2667602 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.8550. Min Range: -12.8550
Max Act: 12.8550. Min Act: -0.1700
Data Index: 4133711 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.8550. Min Range: -12.8550
Max Act: 12.7925. Min Act: -0.1700
Data Index: 1864808 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.8550. Min Range: -12.8550
Max Act: 12.7300. Min Act: -0.1700
Data Index: 5568908 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.8550. Min Range: -12.8550
Max Act: 12.6050. Min Act: -0.1700
Data Index: 7582785 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.8550. Min Range: -12.8550
Max Act: 12.6050. Min Act: -0.1700
Data Index: 3443030 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.8550. Min Range: -12.8550
Max Act: 12.5425. Min Act: -0.1700
Data Index: 1670153 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.8550. Min Range: -12.8550
Max Act: 12.4800. Min Act: -0.1700
Data Index: 5437356 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.8550. Min Range: -12.8550
Max Act: 12.4175. Min Act: -0.1700
Data Index: 4715204 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.8550. Min Range: -12.8550
Max Act: 12.4175. Min Act: -0.1700
Data Index: 3635129 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.8550. Min Range: -12.8550
Max Act: 12.4175. Min Act: -0.1700
Data Index: 2768813 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.8550. Min Range: -12.8550
Max Act: 12.3550. Min Act: -0.1700
Data Index: 1352009 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.8550. Min Range: -12.8550
Max Act: 12.3550. Min Act: -0.1700
Data Index: 5491195 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.8550. Min Range: -12.8550
Max Act: 12.3550. Min Act: -0.1700
Data Index: 6245063 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.8550. Min Range: -12.8550
Max Act: 12.3550. Min Act: -0.1700
Data Index: 2162801 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.8550. Min Range: -12.8550
Max Act: 12.2300. Min Act: -0.1700
Data Index: 6245064 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.8550. Min Range: -12.8550
Max Act: 12.2925. Min Act: -0.1700
Data Index: 7193109 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.8550. Min Range: -12.8550
Max Act: 12.2925. Min Act: -0.1700
Data Index: 3076644 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.8550. Min Range: -12.8550
Max Act: 12.2925. Min Act: -0.1700
Data Index: 2711489 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.8550. Min Range: -12.8550
Max Act: 12.2925. Min Act: -0.1700
Data Index: 5880990 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #19