Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 979 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3088. Min Range: -6.3088
Max Act: 6.3088. Min Act: -0.1700
Data Index: 6639018 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3088. Min Range: -6.3088
Max Act: 6.1838. Min Act: -0.1700
Data Index: 1433209 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3088. Min Range: -6.3088
Max Act: 6.0900. Min Act: -0.1700
Data Index: 1638467 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3088. Min Range: -6.3088
Max Act: 6.0588. Min Act: -0.1700
Data Index: 1743008 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3088. Min Range: -6.3088
Max Act: 5.9963. Min Act: -0.1700
Data Index: 172502 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3088. Min Range: -6.3088
Max Act: 5.9338. Min Act: -0.1700
Data Index: 6745964 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3088. Min Range: -6.3088
Max Act: 5.9338. Min Act: -0.1700
Data Index: 7584034 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3088. Min Range: -6.3088
Max Act: 5.9338. Min Act: -0.1700
Data Index: 5863853 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3088. Min Range: -6.3088
Max Act: 5.9025. Min Act: -0.1700
Data Index: 5380347 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3088. Min Range: -6.3088
Max Act: 5.9025. Min Act: -0.1700
Data Index: 2730087 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3088. Min Range: -6.3088
Max Act: 5.9025. Min Act: -0.1700
Data Index: 5669159 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3088. Min Range: -6.3088
Max Act: 5.9025. Min Act: -0.1700
Data Index: 4050440 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3088. Min Range: -6.3088
Max Act: 5.8713. Min Act: -0.1700
Data Index: 4950467 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3088. Min Range: -6.3088
Max Act: 5.8713. Min Act: -0.1700
Data Index: 3917857 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3088. Min Range: -6.3088
Max Act: 5.8713. Min Act: -0.1700
Data Index: 8533703 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3088. Min Range: -6.3088
Max Act: 5.8400. Min Act: -0.1700
Data Index: 5148367 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3088. Min Range: -6.3088
Max Act: 5.8400. Min Act: -0.1700
Data Index: 6162614 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3088. Min Range: -6.3088
Max Act: 5.8088. Min Act: -0.1700
Data Index: 6342662 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3088. Min Range: -6.3088
Max Act: 5.8088. Min Act: -0.1700
Data Index: 4898489 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3088. Min Range: -6.3088
Max Act: 5.8088. Min Act: -0.1700
Data Index: 747365 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #19