Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4757 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1440. Min Range: -8.1440
Max Act: 8.1440. Min Act: -0.1700
Data Index: 4049371 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1440. Min Range: -8.1440
Max Act: 7.9877. Min Act: -0.1700
Data Index: 8349573 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1440. Min Range: -8.1440
Max Act: 7.9565. Min Act: -0.1700
Data Index: 25845 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1440. Min Range: -8.1440
Max Act: 7.9252. Min Act: -0.1700
Data Index: 5644122 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1440. Min Range: -8.1440
Max Act: 7.9252. Min Act: -0.1700
Data Index: 8118696 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1440. Min Range: -8.1440
Max Act: 7.8940. Min Act: -0.1700
Data Index: 3682146 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1440. Min Range: -8.1440
Max Act: 7.8315. Min Act: -0.1700
Data Index: 145839 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1440. Min Range: -8.1440
Max Act: 7.7690. Min Act: -0.1700
Data Index: 4605062 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1440. Min Range: -8.1440
Max Act: 7.7690. Min Act: -0.1700
Data Index: 6533408 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1440. Min Range: -8.1440
Max Act: 7.7065. Min Act: -0.1700
Data Index: 6930760 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1440. Min Range: -8.1440
Max Act: 7.7690. Min Act: -0.1700
Data Index: 5661082 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1440. Min Range: -8.1440
Max Act: 7.6440. Min Act: -0.1700
Data Index: 5711818 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1440. Min Range: -8.1440
Max Act: 7.6440. Min Act: -0.1700
Data Index: 5711819 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1440. Min Range: -8.1440
Max Act: 7.5815. Min Act: -0.1700
Data Index: 3358187 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1440. Min Range: -8.1440
Max Act: 7.5815. Min Act: -0.1700
Data Index: 8440225 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1440. Min Range: -8.1440
Max Act: 7.5502. Min Act: -0.1700
Data Index: 51784 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1440. Min Range: -8.1440
Max Act: 7.5190. Min Act: -0.1700
Data Index: 832534 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1440. Min Range: -8.1440
Max Act: 7.4877. Min Act: -0.1700
Data Index: 5494386 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1440. Min Range: -8.1440
Max Act: 7.5190. Min Act: -0.1700
Data Index: 8514740 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1440. Min Range: -8.1440
Max Act: 7.4565. Min Act: -0.1700
Data Index: 2359267 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #19