Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5448 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6727. Min Range: -7.6727
Max Act: 7.6727. Min Act: -0.1700
Data Index: 941975 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6727. Min Range: -7.6727
Max Act: 7.6102. Min Act: -0.1700
Data Index: 3788694 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6727. Min Range: -7.6727
Max Act: 7.4227. Min Act: -0.1700
Data Index: 4884745 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6727. Min Range: -7.6727
Max Act: 7.2977. Min Act: -0.1700
Data Index: 1469345 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6727. Min Range: -7.6727
Max Act: 7.2664. Min Act: -0.1700
Data Index: 3323460 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6727. Min Range: -7.6727
Max Act: 7.2039. Min Act: -0.1700
Data Index: 6175054 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6727. Min Range: -7.6727
Max Act: 7.1727. Min Act: -0.1700
Data Index: 4475522 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6727. Min Range: -7.6727
Max Act: 7.1727. Min Act: -0.1700
Data Index: 4382713 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6727. Min Range: -7.6727
Max Act: 7.1102. Min Act: -0.1700
Data Index: 8376633 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6727. Min Range: -7.6727
Max Act: 7.1102. Min Act: -0.1700
Data Index: 7668950 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6727. Min Range: -7.6727
Max Act: 7.1102. Min Act: -0.1700
Data Index: 561011 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6727. Min Range: -7.6727
Max Act: 6.9852. Min Act: -0.1700
Data Index: 8126441 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6727. Min Range: -7.6727
Max Act: 7.0164. Min Act: -0.1700
Data Index: 3169885 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6727. Min Range: -7.6727
Max Act: 6.9852. Min Act: -0.1700
Data Index: 6836007 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6727. Min Range: -7.6727
Max Act: 6.9852. Min Act: -0.1700
Data Index: 5833804 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6727. Min Range: -7.6727
Max Act: 6.9852. Min Act: -0.1700
Data Index: 4338323 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6727. Min Range: -7.6727
Max Act: 6.9227. Min Act: -0.1700
Data Index: 5648743 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6727. Min Range: -7.6727
Max Act: 6.9227. Min Act: -0.1700
Data Index: 4368926 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6727. Min Range: -7.6727
Max Act: 6.8914. Min Act: -0.1700
Data Index: 5130212 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6727. Min Range: -7.6727
Max Act: 6.8914. Min Act: -0.1700
Data Index: 1992467 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #19