Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4604. Min Range: -5.4604
Max Act: 5.4604. Min Act: -0.1700
Data Index: 1707652 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4604. Min Range: -5.4604
Max Act: 5.4604. Min Act: -0.1700
Data Index: 4904993 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4604. Min Range: -5.4604
Max Act: 5.4604. Min Act: -0.1700
Data Index: 5548547 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4604. Min Range: -5.4604
Max Act: 5.4292. Min Act: -0.1700
Data Index: 2036375 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4604. Min Range: -5.4604
Max Act: 5.3979. Min Act: -0.1700
Data Index: 1406809 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4604. Min Range: -5.4604
Max Act: 5.3667. Min Act: -0.1700
Data Index: 7547011 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4604. Min Range: -5.4604
Max Act: 5.3667. Min Act: -0.1700
Data Index: 5234264 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4604. Min Range: -5.4604
Max Act: 5.3042. Min Act: -0.1700
Data Index: 4171191 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4604. Min Range: -5.4604
Max Act: 5.3042. Min Act: -0.1700
Data Index: 2060982 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4604. Min Range: -5.4604
Max Act: 5.3042. Min Act: -0.1700
Data Index: 3985986 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4604. Min Range: -5.4604
Max Act: 5.3042. Min Act: -0.1700
Data Index: 7805545 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4604. Min Range: -5.4604
Max Act: 5.2729. Min Act: -0.1700
Data Index: 6392657 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4604. Min Range: -5.4604
Max Act: 5.2729. Min Act: -0.1700
Data Index: 4549081 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4604. Min Range: -5.4604
Max Act: 5.2729. Min Act: -0.1700
Data Index: 6498561 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4604. Min Range: -5.4604
Max Act: 5.2729. Min Act: -0.1700
Data Index: 4187074 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4604. Min Range: -5.4604
Max Act: 5.2729. Min Act: -0.1700
Data Index: 4172955 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4604. Min Range: -5.4604
Max Act: 5.2104. Min Act: -0.1700
Data Index: 5296541 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4604. Min Range: -5.4604
Max Act: 5.1792. Min Act: -0.1700
Data Index: 34742 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4604. Min Range: -5.4604
Max Act: 5.1792. Min Act: -0.1700
Data Index: 2364375 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4604. Min Range: -5.4604
Max Act: 5.1792. Min Act: -0.1700
Data Index: 2728 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #19