Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1898 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6841. Min Range: -4.6841
Max Act: 4.6841. Min Act: -0.1700
Data Index: 7875108 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6841. Min Range: -4.6841
Max Act: 4.4966. Min Act: -0.1700
Data Index: 6767956 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6841. Min Range: -4.6841
Max Act: 4.4966. Min Act: -0.1700
Data Index: 5491910 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6841. Min Range: -4.6841
Max Act: 4.4654. Min Act: -0.1700
Data Index: 6767938 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6841. Min Range: -4.6841
Max Act: 4.4341. Min Act: -0.1700
Data Index: 1474451 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6841. Min Range: -4.6841
Max Act: 4.4029. Min Act: -0.1700
Data Index: 3820713 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6841. Min Range: -4.6841
Max Act: 4.3716. Min Act: -0.1700
Data Index: 7280348 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6841. Min Range: -4.6841
Max Act: 4.4029. Min Act: -0.1700
Data Index: 6069332 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6841. Min Range: -4.6841
Max Act: 4.3716. Min Act: -0.1700
Data Index: 1695396 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6841. Min Range: -4.6841
Max Act: 4.3716. Min Act: -0.1700
Data Index: 5925079 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6841. Min Range: -4.6841
Max Act: 4.3716. Min Act: -0.1700
Data Index: 4715588 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6841. Min Range: -4.6841
Max Act: 4.3716. Min Act: -0.1700
Data Index: 4805569 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6841. Min Range: -4.6841
Max Act: 4.3404. Min Act: -0.1700
Data Index: 7124991 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6841. Min Range: -4.6841
Max Act: 4.3404. Min Act: -0.1700
Data Index: 5551279 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6841. Min Range: -4.6841
Max Act: 4.3404. Min Act: -0.1700
Data Index: 1469097 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6841. Min Range: -4.6841
Max Act: 4.3091. Min Act: -0.1700
Data Index: 161716 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6841. Min Range: -4.6841
Max Act: 4.3091. Min Act: -0.1700
Data Index: 7109748 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6841. Min Range: -4.6841
Max Act: 4.3091. Min Act: -0.1700
Data Index: 5129622 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6841. Min Range: -4.6841
Max Act: 4.3091. Min Act: -0.1700
Data Index: 669423 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6841. Min Range: -4.6841
Max Act: 4.3091. Min Act: -0.1700
Data Index: 1182160 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19