Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5179 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.8988. Min Act: -0.1700
Data Index: 5976765 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.8363. Min Act: -0.1700
Data Index: 5818978 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.8675. Min Act: -0.1700
Data Index: 1447725 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.7738. Min Act: -0.1700
Data Index: 5717350 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.7425. Min Act: -0.1700
Data Index: 1005509 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.7113. Min Act: -0.1700
Data Index: 5020355 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.6800. Min Act: -0.1700
Data Index: 464951 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.6488. Min Act: -0.1700
Data Index: 4880200 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.6800. Min Act: -0.1700
Data Index: 121757 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.5863. Min Act: -0.1700
Data Index: 2962368 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.6488. Min Act: -0.1700
Data Index: 4970036 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.5863. Min Act: -0.1700
Data Index: 8782673 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.5863. Min Act: -0.1700
Data Index: 6452886 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.5863. Min Act: -0.1700
Data Index: 1388501 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.5238. Min Act: -0.1700
Data Index: 8781503 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.5550. Min Act: -0.1700
Data Index: 1991675 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.5238. Min Act: -0.1700
Data Index: 5383897 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.5550. Min Act: -0.1700
Data Index: 856500 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.5550. Min Act: -0.1700
Data Index: 1485243 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.4925. Min Act: -0.1700
Data Index: 3379800 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #19