Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5937 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9853. Min Range: -5.9853
Max Act: 5.9853. Min Act: -0.1700
Data Index: 1890981 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9853. Min Range: -5.9853
Max Act: 5.9853. Min Act: -0.1700
Data Index: 7031974 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9853. Min Range: -5.9853
Max Act: 5.9228. Min Act: -0.1700
Data Index: 1049516 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9853. Min Range: -5.9853
Max Act: 5.9228. Min Act: -0.1700
Data Index: 5026740 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9853. Min Range: -5.9853
Max Act: 5.9228. Min Act: -0.1700
Data Index: 232907 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9853. Min Range: -5.9853
Max Act: 5.8603. Min Act: -0.1700
Data Index: 8614580 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9853. Min Range: -5.9853
Max Act: 5.8916. Min Act: -0.1700
Data Index: 7907031 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9853. Min Range: -5.9853
Max Act: 5.8603. Min Act: -0.1700
Data Index: 232751 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9853. Min Range: -5.9853
Max Act: 5.8603. Min Act: -0.1700
Data Index: 4279919 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9853. Min Range: -5.9853
Max Act: 5.8603. Min Act: -0.1700
Data Index: 5407069 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9853. Min Range: -5.9853
Max Act: 5.8603. Min Act: -0.1700
Data Index: 6906797 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9853. Min Range: -5.9853
Max Act: 5.7666. Min Act: -0.1700
Data Index: 3413388 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9853. Min Range: -5.9853
Max Act: 5.7353. Min Act: -0.1700
Data Index: 4684010 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9853. Min Range: -5.9853
Max Act: 5.7666. Min Act: -0.1700
Data Index: 7240105 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9853. Min Range: -5.9853
Max Act: 5.7666. Min Act: -0.1700
Data Index: 347049 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9853. Min Range: -5.9853
Max Act: 5.7353. Min Act: -0.1700
Data Index: 5009007 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9853. Min Range: -5.9853
Max Act: 5.7353. Min Act: -0.1700
Data Index: 2019522 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9853. Min Range: -5.9853
Max Act: 5.6728. Min Act: -0.1700
Data Index: 3704826 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9853. Min Range: -5.9853
Max Act: 5.7041. Min Act: -0.1700
Data Index: 2235647 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9853. Min Range: -5.9853
Max Act: 5.6728. Min Act: -0.1700
Data Index: 34472 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #19