Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4006 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9827. Min Range: -6.9827
Max Act: 6.9827. Min Act: -0.1700
Data Index: 7168862 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9827. Min Range: -6.9827
Max Act: 6.9827. Min Act: -0.1700
Data Index: 6940169 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9827. Min Range: -6.9827
Max Act: 6.9515. Min Act: -0.1700
Data Index: 4308481 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9827. Min Range: -6.9827
Max Act: 6.8577. Min Act: -0.1700
Data Index: 5226124 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9827. Min Range: -6.9827
Max Act: 6.8577. Min Act: -0.1700
Data Index: 5876890 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9827. Min Range: -6.9827
Max Act: 6.8265. Min Act: -0.1700
Data Index: 5883916 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9827. Min Range: -6.9827
Max Act: 6.7952. Min Act: -0.1700
Data Index: 7675524 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9827. Min Range: -6.9827
Max Act: 6.7640. Min Act: -0.1700
Data Index: 281094 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9827. Min Range: -6.9827
Max Act: 6.7640. Min Act: -0.1700
Data Index: 2222963 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9827. Min Range: -6.9827
Max Act: 6.7327. Min Act: -0.1700
Data Index: 6308709 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9827. Min Range: -6.9827
Max Act: 6.6390. Min Act: -0.1700
Data Index: 666727 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9827. Min Range: -6.9827
Max Act: 6.6390. Min Act: -0.1700
Data Index: 4361013 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9827. Min Range: -6.9827
Max Act: 6.6702. Min Act: -0.1700
Data Index: 822493 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9827. Min Range: -6.9827
Max Act: 6.6077. Min Act: -0.1700
Data Index: 7663282 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9827. Min Range: -6.9827
Max Act: 6.5765. Min Act: -0.1700
Data Index: 4406043 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9827. Min Range: -6.9827
Max Act: 6.6077. Min Act: -0.1700
Data Index: 3689811 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9827. Min Range: -6.9827
Max Act: 6.6077. Min Act: -0.1700
Data Index: 4411855 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9827. Min Range: -6.9827
Max Act: 6.5765. Min Act: -0.1700
Data Index: 4632358 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9827. Min Range: -6.9827
Max Act: 6.6390. Min Act: -0.1700
Data Index: 7757248 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9827. Min Range: -6.9827
Max Act: 6.6390. Min Act: -0.1700
Data Index: 5883942 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #19