Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2992 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.1627. Min Range: -12.1627
Max Act: 12.1627. Min Act: -0.1700
Data Index: 3268638 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.1627. Min Range: -12.1627
Max Act: 12.0377. Min Act: -0.1700
Data Index: 1882084 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.1627. Min Range: -12.1627
Max Act: 11.6627. Min Act: -0.1700
Data Index: 7520191 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.1627. Min Range: -12.1627
Max Act: 11.5377. Min Act: -0.1700
Data Index: 2696800 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.1627. Min Range: -12.1627
Max Act: 11.4752. Min Act: -0.1700
Data Index: 8759925 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.1627. Min Range: -12.1627
Max Act: 11.3502. Min Act: -0.1700
Data Index: 1390908 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.1627. Min Range: -12.1627
Max Act: 11.3502. Min Act: -0.1700
Data Index: 5807758 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.1627. Min Range: -12.1627
Max Act: 11.2877. Min Act: -0.1700
Data Index: 6906530 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.1627. Min Range: -12.1627
Max Act: 11.1627. Min Act: -0.1700
Data Index: 470460 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.1627. Min Range: -12.1627
Max Act: 11.1627. Min Act: -0.1700
Data Index: 7065633 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.1627. Min Range: -12.1627
Max Act: 11.1627. Min Act: -0.1700
Data Index: 6951581 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.1627. Min Range: -12.1627
Max Act: 11.1627. Min Act: -0.1700
Data Index: 2471134 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.1627. Min Range: -12.1627
Max Act: 11.1002. Min Act: -0.1700
Data Index: 4371751 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.1627. Min Range: -12.1627
Max Act: 11.1002. Min Act: -0.1700
Data Index: 7601177 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.1627. Min Range: -12.1627
Max Act: 11.0377. Min Act: -0.1700
Data Index: 4227081 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.1627. Min Range: -12.1627
Max Act: 11.0377. Min Act: -0.1700
Data Index: 7714906 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.1627. Min Range: -12.1627
Max Act: 11.0377. Min Act: -0.1700
Data Index: 957538 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.1627. Min Range: -12.1627
Max Act: 10.9752. Min Act: -0.1700
Data Index: 434320 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.1627. Min Range: -12.1627
Max Act: 10.9752. Min Act: -0.1700
Data Index: 7350560 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.1627. Min Range: -12.1627
Max Act: 10.9752. Min Act: -0.1700
Data Index: 2324962 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #19