Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2538 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6681. Min Range: -6.6681
Max Act: 6.6681. Min Act: -0.1700
Data Index: 523215 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6681. Min Range: -6.6681
Max Act: 6.6368. Min Act: -0.1700
Data Index: 3844315 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6681. Min Range: -6.6681
Max Act: 6.3243. Min Act: -0.1700
Data Index: 3226304 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6681. Min Range: -6.6681
Max Act: 6.1993. Min Act: -0.1700
Data Index: 1485113 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6681. Min Range: -6.6681
Max Act: 6.1681. Min Act: -0.1700
Data Index: 3678083 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6681. Min Range: -6.6681
Max Act: 6.1368. Min Act: -0.1700
Data Index: 6807034 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6681. Min Range: -6.6681
Max Act: 6.1368. Min Act: -0.1700
Data Index: 6951172 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6681. Min Range: -6.6681
Max Act: 6.0743. Min Act: -0.1700
Data Index: 7121152 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6681. Min Range: -6.6681
Max Act: 6.0743. Min Act: -0.1700
Data Index: 840096 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6681. Min Range: -6.6681
Max Act: 6.0431. Min Act: -0.1700
Data Index: 2374041 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6681. Min Range: -6.6681
Max Act: 5.9806. Min Act: -0.1700
Data Index: 5625809 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6681. Min Range: -6.6681
Max Act: 5.9181. Min Act: -0.1700
Data Index: 7836751 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6681. Min Range: -6.6681
Max Act: 5.8868. Min Act: -0.1700
Data Index: 4159555 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6681. Min Range: -6.6681
Max Act: 5.8868. Min Act: -0.1700
Data Index: 4026834 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6681. Min Range: -6.6681
Max Act: 5.8868. Min Act: -0.1700
Data Index: 1248606 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6681. Min Range: -6.6681
Max Act: 5.8868. Min Act: -0.1700
Data Index: 3093170 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6681. Min Range: -6.6681
Max Act: 5.9181. Min Act: -0.1700
Data Index: 7836525 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6681. Min Range: -6.6681
Max Act: 5.8243. Min Act: -0.1700
Data Index: 4612103 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6681. Min Range: -6.6681
Max Act: 5.8243. Min Act: -0.1700
Data Index: 4788626 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6681. Min Range: -6.6681
Max Act: 5.8556. Min Act: -0.1700
Data Index: 7397856 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #19