Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3587 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4433. Min Range: -8.4433
Max Act: 8.4433. Min Act: -0.1700
Data Index: 5771120 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4433. Min Range: -8.4433
Max Act: 8.2558. Min Act: -0.1700
Data Index: 3516546 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4433. Min Range: -8.4433
Max Act: 8.1933. Min Act: -0.1700
Data Index: 4345998 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4433. Min Range: -8.4433
Max Act: 8.0995. Min Act: -0.1700
Data Index: 1246671 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4433. Min Range: -8.4433
Max Act: 8.0058. Min Act: -0.1700
Data Index: 7017886 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4433. Min Range: -8.4433
Max Act: 7.9433. Min Act: -0.1700
Data Index: 5439673 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4433. Min Range: -8.4433
Max Act: 7.9433. Min Act: -0.1700
Data Index: 4567655 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4433. Min Range: -8.4433
Max Act: 7.9433. Min Act: -0.1700
Data Index: 6976453 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4433. Min Range: -8.4433
Max Act: 7.9120. Min Act: -0.1700
Data Index: 6881493 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4433. Min Range: -8.4433
Max Act: 7.8495. Min Act: -0.1699
Data Index: 8265359 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4433. Min Range: -8.4433
Max Act: 7.8183. Min Act: -0.1700
Data Index: 5832314 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4433. Min Range: -8.4433
Max Act: 7.8183. Min Act: -0.1700
Data Index: 2028391 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4433. Min Range: -8.4433
Max Act: 7.8495. Min Act: -0.1700
Data Index: 7723181 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4433. Min Range: -8.4433
Max Act: 7.8183. Min Act: -0.1700
Data Index: 5736000 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4433. Min Range: -8.4433
Max Act: 7.8183. Min Act: -0.1700
Data Index: 3969016 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4433. Min Range: -8.4433
Max Act: 7.7558. Min Act: -0.1700
Data Index: 6363998 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4433. Min Range: -8.4433
Max Act: 7.7870. Min Act: -0.1700
Data Index: 2657605 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4433. Min Range: -8.4433
Max Act: 7.7870. Min Act: -0.1700
Data Index: 8265347 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4433. Min Range: -8.4433
Max Act: 7.7558. Min Act: -0.1700
Data Index: 4034806 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4433. Min Range: -8.4433
Max Act: 7.7245. Min Act: -0.1700
Data Index: 665112 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19