Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 363 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3323. Min Range: -6.3323
Max Act: 6.3323. Min Act: -0.1700
Data Index: 5048884 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3323. Min Range: -6.3323
Max Act: 6.3010. Min Act: -0.1700
Data Index: 5048908 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3323. Min Range: -6.3323
Max Act: 6.3010. Min Act: -0.1700
Data Index: 5048882 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3323. Min Range: -6.3323
Max Act: 6.2698. Min Act: -0.1700
Data Index: 5048910 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3323. Min Range: -6.3323
Max Act: 5.8948. Min Act: -0.1700
Data Index: 5048873 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3323. Min Range: -6.3323
Max Act: 5.8323. Min Act: -0.1700
Data Index: 5291478 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3323. Min Range: -6.3323
Max Act: 5.8010. Min Act: -0.1700
Data Index: 544013 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3323. Min Range: -6.3323
Max Act: 5.7385. Min Act: -0.1700
Data Index: 7865698 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3323. Min Range: -6.3323
Max Act: 5.7073. Min Act: -0.1700
Data Index: 7225733 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3323. Min Range: -6.3323
Max Act: 5.6448. Min Act: -0.1700
Data Index: 4094568 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3323. Min Range: -6.3323
Max Act: 5.6135. Min Act: -0.1700
Data Index: 2670196 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3323. Min Range: -6.3323
Max Act: 5.6448. Min Act: -0.1700
Data Index: 26389 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3323. Min Range: -6.3323
Max Act: 5.5823. Min Act: -0.1700
Data Index: 8749545 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3323. Min Range: -6.3323
Max Act: 5.5823. Min Act: -0.1700
Data Index: 5048900 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3323. Min Range: -6.3323
Max Act: 5.5510. Min Act: -0.1700
Data Index: 1029408 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3323. Min Range: -6.3323
Max Act: 5.5510. Min Act: -0.1700
Data Index: 4375440 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3323. Min Range: -6.3323
Max Act: 5.5198. Min Act: -0.1700
Data Index: 5048890 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3323. Min Range: -6.3323
Max Act: 5.4885. Min Act: -0.1700
Data Index: 5385096 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3323. Min Range: -6.3323
Max Act: 5.4573. Min Act: -0.1700
Data Index: 6876457 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3323. Min Range: -6.3323
Max Act: 5.4573. Min Act: -0.1700
Data Index: 6275591 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #19