Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5871 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7784. Min Range: -6.7784
Max Act: 6.7784. Min Act: -0.1700
Data Index: 2013232 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7784. Min Range: -6.7784
Max Act: 6.6847. Min Act: -0.1700
Data Index: 5953583 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7784. Min Range: -6.7784
Max Act: 6.6847. Min Act: -0.1700
Data Index: 7322856 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7784. Min Range: -6.7784
Max Act: 6.6847. Min Act: -0.1700
Data Index: 1299608 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7784. Min Range: -6.7784
Max Act: 6.6534. Min Act: -0.1700
Data Index: 5169214 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7784. Min Range: -6.7784
Max Act: 6.6534. Min Act: -0.1700
Data Index: 6810605 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7784. Min Range: -6.7784
Max Act: 6.5909. Min Act: -0.1700
Data Index: 8773224 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7784. Min Range: -6.7784
Max Act: 6.5909. Min Act: -0.1700
Data Index: 7606638 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7784. Min Range: -6.7784
Max Act: 6.5597. Min Act: -0.1700
Data Index: 4236448 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7784. Min Range: -6.7784
Max Act: 6.5909. Min Act: -0.1700
Data Index: 6643906 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7784. Min Range: -6.7784
Max Act: 6.5909. Min Act: -0.1700
Data Index: 6933784 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7784. Min Range: -6.7784
Max Act: 6.5597. Min Act: -0.1700
Data Index: 5261378 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7784. Min Range: -6.7784
Max Act: 6.5597. Min Act: -0.1700
Data Index: 7054243 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7784. Min Range: -6.7784
Max Act: 6.5284. Min Act: -0.1700
Data Index: 6947469 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7784. Min Range: -6.7784
Max Act: 6.5284. Min Act: -0.1700
Data Index: 420129 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7784. Min Range: -6.7784
Max Act: 6.4972. Min Act: -0.1700
Data Index: 3604100 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7784. Min Range: -6.7784
Max Act: 6.4972. Min Act: -0.1700
Data Index: 3157403 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7784. Min Range: -6.7784
Max Act: 6.4659. Min Act: -0.1700
Data Index: 6178507 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7784. Min Range: -6.7784
Max Act: 6.4659. Min Act: -0.1700
Data Index: 2622661 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7784. Min Range: -6.7784
Max Act: 6.4659. Min Act: -0.1700
Data Index: 2870836 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #19