Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2727 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3774. Min Range: -8.3774
Max Act: 8.3774. Min Act: -0.1700
Data Index: 177091 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3774. Min Range: -8.3774
Max Act: 8.2524. Min Act: -0.1700
Data Index: 4634552 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3774. Min Range: -8.3774
Max Act: 7.8774. Min Act: -0.1700
Data Index: 4845777 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3774. Min Range: -8.3774
Max Act: 7.8149. Min Act: -0.1700
Data Index: 6563613 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3774. Min Range: -8.3774
Max Act: 7.7524. Min Act: -0.1700
Data Index: 4586772 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3774. Min Range: -8.3774
Max Act: 7.7211. Min Act: -0.1700
Data Index: 8179320 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3774. Min Range: -8.3774
Max Act: 7.7211. Min Act: -0.1700
Data Index: 1810631 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3774. Min Range: -8.3774
Max Act: 7.7211. Min Act: -0.1700
Data Index: 2523037 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3774. Min Range: -8.3774
Max Act: 7.7211. Min Act: -0.1700
Data Index: 869531 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3774. Min Range: -8.3774
Max Act: 7.6899. Min Act: -0.1700
Data Index: 6770450 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3774. Min Range: -8.3774
Max Act: 7.6899. Min Act: -0.1700
Data Index: 5200237 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3774. Min Range: -8.3774
Max Act: 7.6586. Min Act: -0.1700
Data Index: 4944880 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3774. Min Range: -8.3774
Max Act: 7.6274. Min Act: -0.1700
Data Index: 3923936 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3774. Min Range: -8.3774
Max Act: 7.6274. Min Act: -0.1700
Data Index: 129011 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3774. Min Range: -8.3774
Max Act: 7.6274. Min Act: -0.1700
Data Index: 7504558 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3774. Min Range: -8.3774
Max Act: 7.5649. Min Act: -0.1700
Data Index: 6330798 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3774. Min Range: -8.3774
Max Act: 7.5649. Min Act: -0.1700
Data Index: 1555946 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3774. Min Range: -8.3774
Max Act: 7.5649. Min Act: -0.1700
Data Index: 3279673 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3774. Min Range: -8.3774
Max Act: 7.5649. Min Act: -0.1700
Data Index: 4218252 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3774. Min Range: -8.3774
Max Act: 7.5336. Min Act: -0.1700
Data Index: 3743972 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #19