Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3777 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9854. Min Range: -2.9854
Max Act: 2.9854. Min Act: -0.1700
Data Index: 1626024 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9854. Min Range: -2.9854
Max Act: 2.9696. Min Act: -0.1700
Data Index: 3336367 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9854. Min Range: -2.9854
Max Act: 2.9379. Min Act: -0.1700
Data Index: 5300676 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9854. Min Range: -2.9854
Max Act: 2.9221. Min Act: -0.1700
Data Index: 7150927 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9854. Min Range: -2.9854
Max Act: 2.9221. Min Act: -0.1700
Data Index: 6567724 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9854. Min Range: -2.9854
Max Act: 2.9062. Min Act: -0.1700
Data Index: 8787742 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9854. Min Range: -2.9854
Max Act: 2.9062. Min Act: -0.1700
Data Index: 8753518 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9854. Min Range: -2.9854
Max Act: 2.9062. Min Act: -0.1700
Data Index: 8461620 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9854. Min Range: -2.9854
Max Act: 2.9062. Min Act: -0.1700
Data Index: 5395516 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9854. Min Range: -2.9854
Max Act: 2.8904. Min Act: -0.1700
Data Index: 3240907 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9854. Min Range: -2.9854
Max Act: 2.8745. Min Act: -0.1700
Data Index: 4715492 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9854. Min Range: -2.9854
Max Act: 2.8745. Min Act: -0.1700
Data Index: 2712007 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9854. Min Range: -2.9854
Max Act: 2.8745. Min Act: -0.1700
Data Index: 2280938 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9854. Min Range: -2.9854
Max Act: 2.8427. Min Act: -0.1700
Data Index: 3769714 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9854. Min Range: -2.9854
Max Act: 2.8586. Min Act: -0.1700
Data Index: 1410569 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9854. Min Range: -2.9854
Max Act: 2.8586. Min Act: -0.1700
Data Index: 8510904 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9854. Min Range: -2.9854
Max Act: 2.8586. Min Act: -0.1700
Data Index: 326944 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9854. Min Range: -2.9854
Max Act: 2.8427. Min Act: -0.1700
Data Index: 5394002 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9854. Min Range: -2.9854
Max Act: 2.8427. Min Act: -0.1700
Data Index: 3204776 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9854. Min Range: -2.9854
Max Act: 2.8427. Min Act: -0.1700
Data Index: 5927677 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19