Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1273 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2854. Min Range: -5.2854
Max Act: 5.2854. Min Act: -0.1700
Data Index: 5217272 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2854. Min Range: -5.2854
Max Act: 5.2541. Min Act: -0.1700
Data Index: 6406149 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2854. Min Range: -5.2854
Max Act: 5.2229. Min Act: -0.1700
Data Index: 5270522 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2854. Min Range: -5.2854
Max Act: 5.1604. Min Act: -0.1700
Data Index: 4077760 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2854. Min Range: -5.2854
Max Act: 5.1604. Min Act: -0.1700
Data Index: 94798 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2854. Min Range: -5.2854
Max Act: 5.1291. Min Act: -0.1700
Data Index: 8314479 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2854. Min Range: -5.2854
Max Act: 5.1291. Min Act: -0.1700
Data Index: 532313 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2854. Min Range: -5.2854
Max Act: 5.0666. Min Act: -0.1700
Data Index: 639098 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2854. Min Range: -5.2854
Max Act: 5.0666. Min Act: -0.1700
Data Index: 3083020 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2854. Min Range: -5.2854
Max Act: 5.0354. Min Act: -0.1700
Data Index: 4453950 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2854. Min Range: -5.2854
Max Act: 5.0354. Min Act: -0.1700
Data Index: 4715598 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2854. Min Range: -5.2854
Max Act: 5.0041. Min Act: -0.1700
Data Index: 5484024 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2854. Min Range: -5.2854
Max Act: 4.9729. Min Act: -0.1700
Data Index: 3821885 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2854. Min Range: -5.2854
Max Act: 4.9729. Min Act: -0.1700
Data Index: 3502393 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2854. Min Range: -5.2854
Max Act: 4.9416. Min Act: -0.1700
Data Index: 558879 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2854. Min Range: -5.2854
Max Act: 4.9729. Min Act: -0.1700
Data Index: 2391876 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2854. Min Range: -5.2854
Max Act: 4.9416. Min Act: -0.1700
Data Index: 299446 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2854. Min Range: -5.2854
Max Act: 4.9416. Min Act: -0.1700
Data Index: 8756832 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2854. Min Range: -5.2854
Max Act: 4.9416. Min Act: -0.1700
Data Index: 6538278 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2854. Min Range: -5.2854
Max Act: 4.8791. Min Act: -0.1700
Data Index: 4565820 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #19