Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2927 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1886. Min Range: -6.1886
Max Act: 6.1886. Min Act: -0.1700
Data Index: 7176172 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1886. Min Range: -6.1886
Max Act: 6.0636. Min Act: -0.1700
Data Index: 5227105 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1886. Min Range: -6.1886
Max Act: 6.0636. Min Act: -0.1700
Data Index: 1114019 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1886. Min Range: -6.1886
Max Act: 6.0011. Min Act: -0.1700
Data Index: 2830340 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1886. Min Range: -6.1886
Max Act: 5.9699. Min Act: -0.1700
Data Index: 7086072 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1886. Min Range: -6.1886
Max Act: 5.9074. Min Act: -0.1700
Data Index: 7974230 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1886. Min Range: -6.1886
Max Act: 5.8761. Min Act: -0.1700
Data Index: 3137379 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1886. Min Range: -6.1886
Max Act: 5.8761. Min Act: -0.1700
Data Index: 2925472 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1886. Min Range: -6.1886
Max Act: 5.8449. Min Act: -0.1700
Data Index: 1580593 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1886. Min Range: -6.1886
Max Act: 5.7824. Min Act: -0.1700
Data Index: 4448572 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1886. Min Range: -6.1886
Max Act: 5.8136. Min Act: -0.1700
Data Index: 1514759 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1886. Min Range: -6.1886
Max Act: 5.6886. Min Act: -0.1700
Data Index: 6128245 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1886. Min Range: -6.1886
Max Act: 5.7199. Min Act: -0.1700
Data Index: 1974468 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1886. Min Range: -6.1886
Max Act: 5.6886. Min Act: -0.1700
Data Index: 988333 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1886. Min Range: -6.1886
Max Act: 5.6886. Min Act: -0.1700
Data Index: 5888126 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1886. Min Range: -6.1886
Max Act: 5.7199. Min Act: -0.1700
Data Index: 3481859 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1886. Min Range: -6.1886
Max Act: 5.6886. Min Act: -0.1700
Data Index: 8727485 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1886. Min Range: -6.1886
Max Act: 5.6574. Min Act: -0.1700
Data Index: 7834984 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1886. Min Range: -6.1886
Max Act: 5.6574. Min Act: -0.1700
Data Index: 5105692 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1886. Min Range: -6.1886
Max Act: 5.6574. Min Act: -0.1700
Data Index: 503002 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #19