Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5414 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1697. Min Range: -6.1697
Max Act: 6.1697. Min Act: -0.1700
Data Index: 1582832 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1697. Min Range: -6.1697
Max Act: 5.7634. Min Act: -0.1700
Data Index: 7930551 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1697. Min Range: -6.1697
Max Act: 5.7322. Min Act: -0.1700
Data Index: 4506215 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1697. Min Range: -6.1697
Max Act: 5.6697. Min Act: -0.1700
Data Index: 5133012 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1697. Min Range: -6.1697
Max Act: 5.6072. Min Act: -0.1700
Data Index: 6593963 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1697. Min Range: -6.1697
Max Act: 5.6072. Min Act: -0.1700
Data Index: 506897 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1697. Min Range: -6.1697
Max Act: 5.6072. Min Act: -0.1700
Data Index: 6327026 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1697. Min Range: -6.1697
Max Act: 5.5759. Min Act: -0.1700
Data Index: 2912522 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1697. Min Range: -6.1697
Max Act: 5.5134. Min Act: -0.1700
Data Index: 4539082 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1697. Min Range: -6.1697
Max Act: 5.5134. Min Act: -0.1700
Data Index: 5380103 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1697. Min Range: -6.1697
Max Act: 5.5134. Min Act: -0.1700
Data Index: 1316953 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1697. Min Range: -6.1697
Max Act: 5.5134. Min Act: -0.1700
Data Index: 4443290 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1697. Min Range: -6.1697
Max Act: 5.4822. Min Act: -0.1700
Data Index: 7575919 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1697. Min Range: -6.1697
Max Act: 5.4822. Min Act: -0.1700
Data Index: 4555305 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1697. Min Range: -6.1697
Max Act: 5.4822. Min Act: -0.1700
Data Index: 6511399 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1697. Min Range: -6.1697
Max Act: 5.4509. Min Act: -0.1700
Data Index: 26779 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1697. Min Range: -6.1697
Max Act: 5.4822. Min Act: -0.1700
Data Index: 462889 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1697. Min Range: -6.1697
Max Act: 5.4509. Min Act: -0.1700
Data Index: 778620 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1697. Min Range: -6.1697
Max Act: 5.4509. Min Act: -0.1700
Data Index: 221610 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1697. Min Range: -6.1697
Max Act: 5.4197. Min Act: -0.1700
Data Index: 7250697 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #19