Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 37 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1083. Min Range: -6.1083
Max Act: 6.1083. Min Act: -0.1700
Data Index: 7303412 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1083. Min Range: -6.1083
Max Act: 6.0146. Min Act: -0.1700
Data Index: 2968096 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1083. Min Range: -6.1083
Max Act: 5.9833. Min Act: -0.1700
Data Index: 18344 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1083. Min Range: -6.1083
Max Act: 6.0146. Min Act: -0.1700
Data Index: 5154202 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1083. Min Range: -6.1083
Max Act: 5.9833. Min Act: -0.1700
Data Index: 4307166 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1083. Min Range: -6.1083
Max Act: 5.9208. Min Act: -0.1700
Data Index: 4859546 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1083. Min Range: -6.1083
Max Act: 5.9208. Min Act: -0.1700
Data Index: 5929064 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1083. Min Range: -6.1083
Max Act: 5.8896. Min Act: -0.1700
Data Index: 7805445 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1083. Min Range: -6.1083
Max Act: 5.8896. Min Act: -0.1700
Data Index: 6826434 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1083. Min Range: -6.1083
Max Act: 5.8583. Min Act: -0.1700
Data Index: 410721 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1083. Min Range: -6.1083
Max Act: 5.8583. Min Act: -0.1700
Data Index: 6346373 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1083. Min Range: -6.1083
Max Act: 5.8583. Min Act: -0.1700
Data Index: 6057960 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1083. Min Range: -6.1083
Max Act: 5.8271. Min Act: -0.1700
Data Index: 7359013 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1083. Min Range: -6.1083
Max Act: 5.8271. Min Act: -0.1700
Data Index: 8201235 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1083. Min Range: -6.1083
Max Act: 5.8271. Min Act: -0.1700
Data Index: 8081569 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1083. Min Range: -6.1083
Max Act: 5.7958. Min Act: -0.1700
Data Index: 8070145 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1083. Min Range: -6.1083
Max Act: 5.8271. Min Act: -0.1700
Data Index: 7510107 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1083. Min Range: -6.1083
Max Act: 5.7958. Min Act: -0.1700
Data Index: 4333903 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1083. Min Range: -6.1083
Max Act: 5.7958. Min Act: -0.1700
Data Index: 6297454 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1083. Min Range: -6.1083
Max Act: 5.7958. Min Act: -0.1700
Data Index: 6860477 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19