Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5057 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6919. Min Range: -6.6919
Max Act: 6.6919. Min Act: -0.1700
Data Index: 2702232 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6919. Min Range: -6.6919
Max Act: 6.6919. Min Act: -0.1700
Data Index: 3294847 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6919. Min Range: -6.6919
Max Act: 6.6607. Min Act: -0.1700
Data Index: 7374209 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6919. Min Range: -6.6919
Max Act: 6.6294. Min Act: -0.1700
Data Index: 5910857 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6919. Min Range: -6.6919
Max Act: 6.6294. Min Act: -0.1700
Data Index: 3125082 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6919. Min Range: -6.6919
Max Act: 6.6294. Min Act: -0.1700
Data Index: 6982472 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6919. Min Range: -6.6919
Max Act: 6.5669. Min Act: -0.1700
Data Index: 8216317 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6919. Min Range: -6.6919
Max Act: 6.5357. Min Act: -0.1700
Data Index: 6754577 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6919. Min Range: -6.6919
Max Act: 6.5357. Min Act: -0.1700
Data Index: 2250005 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6919. Min Range: -6.6919
Max Act: 6.5044. Min Act: -0.1700
Data Index: 2896507 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6919. Min Range: -6.6919
Max Act: 6.5357. Min Act: -0.1700
Data Index: 4792180 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6919. Min Range: -6.6919
Max Act: 6.4732. Min Act: -0.1700
Data Index: 572034 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6919. Min Range: -6.6919
Max Act: 6.4732. Min Act: -0.1700
Data Index: 5550462 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6919. Min Range: -6.6919
Max Act: 6.4419. Min Act: -0.1700
Data Index: 4208297 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6919. Min Range: -6.6919
Max Act: 6.4419. Min Act: -0.1700
Data Index: 8598929 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6919. Min Range: -6.6919
Max Act: 6.4107. Min Act: -0.1700
Data Index: 6807205 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6919. Min Range: -6.6919
Max Act: 6.3794. Min Act: -0.1700
Data Index: 6775780 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6919. Min Range: -6.6919
Max Act: 6.4107. Min Act: -0.1700
Data Index: 6977937 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6919. Min Range: -6.6919
Max Act: 6.4107. Min Act: -0.1700
Data Index: 1384705 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6919. Min Range: -6.6919
Max Act: 6.4107. Min Act: -0.1700
Data Index: 3023693 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19