Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3256 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9702. Min Range: -7.9702
Max Act: 7.9702. Min Act: -0.1700
Data Index: 1903817 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9702. Min Range: -7.9702
Max Act: 7.9077. Min Act: -0.1700
Data Index: 3576040 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9702. Min Range: -7.9702
Max Act: 7.7827. Min Act: -0.1700
Data Index: 234683 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9702. Min Range: -7.9702
Max Act: 7.7514. Min Act: -0.1700
Data Index: 3280392 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9702. Min Range: -7.9702
Max Act: 7.7514. Min Act: -0.1700
Data Index: 8336028 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9702. Min Range: -7.9702
Max Act: 7.6889. Min Act: -0.1700
Data Index: 8394837 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9702. Min Range: -7.9702
Max Act: 7.6577. Min Act: -0.1700
Data Index: 3018158 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9702. Min Range: -7.9702
Max Act: 7.5639. Min Act: -0.1700
Data Index: 2377356 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9702. Min Range: -7.9702
Max Act: 7.5639. Min Act: -0.1700
Data Index: 6519754 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9702. Min Range: -7.9702
Max Act: 7.5639. Min Act: -0.1700
Data Index: 816270 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9702. Min Range: -7.9702
Max Act: 7.5639. Min Act: -0.1700
Data Index: 6171127 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9702. Min Range: -7.9702
Max Act: 7.5327. Min Act: -0.1700
Data Index: 7451761 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9702. Min Range: -7.9702
Max Act: 7.5327. Min Act: -0.1700
Data Index: 3378859 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9702. Min Range: -7.9702
Max Act: 7.5014. Min Act: -0.1700
Data Index: 6834979 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9702. Min Range: -7.9702
Max Act: 7.4389. Min Act: -0.1700
Data Index: 1350577 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9702. Min Range: -7.9702
Max Act: 7.4702. Min Act: -0.1700
Data Index: 595861 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9702. Min Range: -7.9702
Max Act: 7.4389. Min Act: -0.1700
Data Index: 5367320 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9702. Min Range: -7.9702
Max Act: 7.3764. Min Act: -0.1700
Data Index: 3148112 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9702. Min Range: -7.9702
Max Act: 7.4077. Min Act: -0.1700
Data Index: 2764015 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9702. Min Range: -7.9702
Max Act: 7.3764. Min Act: -0.1700
Data Index: 3858217 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19