Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3554 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9699. Min Range: -6.9699
Max Act: 6.9699. Min Act: -0.1700
Data Index: 7786780 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9699. Min Range: -6.9699
Max Act: 6.8761. Min Act: -0.1700
Data Index: 8363624 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9699. Min Range: -6.9699
Max Act: 6.9074. Min Act: -0.1700
Data Index: 6129766 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9699. Min Range: -6.9699
Max Act: 6.8761. Min Act: -0.1700
Data Index: 8519444 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9699. Min Range: -6.9699
Max Act: 6.9386. Min Act: -0.1700
Data Index: 3332746 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9699. Min Range: -6.9699
Max Act: 6.9074. Min Act: -0.1700
Data Index: 2921050 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9699. Min Range: -6.9699
Max Act: 6.9074. Min Act: -0.1700
Data Index: 4999399 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9699. Min Range: -6.9699
Max Act: 6.9074. Min Act: -0.1700
Data Index: 8519417 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9699. Min Range: -6.9699
Max Act: 6.8761. Min Act: -0.1700
Data Index: 8519436 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9699. Min Range: -6.9699
Max Act: 6.8761. Min Act: -0.1700
Data Index: 8519446 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9699. Min Range: -6.9699
Max Act: 6.8449. Min Act: -0.1700
Data Index: 4533810 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9699. Min Range: -6.9699
Max Act: 6.8449. Min Act: -0.1700
Data Index: 2717603 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9699. Min Range: -6.9699
Max Act: 6.8449. Min Act: -0.1700
Data Index: 5278529 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9699. Min Range: -6.9699
Max Act: 6.8136. Min Act: -0.1700
Data Index: 6803735 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9699. Min Range: -6.9699
Max Act: 6.8449. Min Act: -0.1700
Data Index: 7119453 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9699. Min Range: -6.9699
Max Act: 6.8136. Min Act: -0.1700
Data Index: 7529147 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9699. Min Range: -6.9699
Max Act: 6.8449. Min Act: -0.1700
Data Index: 7759055 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9699. Min Range: -6.9699
Max Act: 6.8761. Min Act: -0.1700
Data Index: 602940 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9699. Min Range: -6.9699
Max Act: 6.8136. Min Act: -0.1700
Data Index: 7319303 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9699. Min Range: -6.9699
Max Act: 6.8136. Min Act: -0.1700
Data Index: 7525875 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #19