Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3755 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.0718. Min Range: -1.0718
Max Act: 1.0718. Min Act: -0.1700
Data Index: 4828080 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0718. Min Range: -1.0718
Max Act: 1.0282. Min Act: -0.1700
Data Index: 7950968 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0718. Min Range: -1.0718
Max Act: 1.0108. Min Act: -0.1700
Data Index: 8313662 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0718. Min Range: -1.0718
Max Act: 0.9847. Min Act: -0.1700
Data Index: 7705661 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0718. Min Range: -1.0718
Max Act: 0.9761. Min Act: -0.1700
Data Index: 8607367 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0718. Min Range: -1.0718
Max Act: 0.9674. Min Act: -0.1700
Data Index: 763082 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0718. Min Range: -1.0718
Max Act: 0.9588. Min Act: -0.1698
Data Index: 302078 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0718. Min Range: -1.0718
Max Act: 0.9502. Min Act: -0.1699
Data Index: 7302666 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0718. Min Range: -1.0718
Max Act: 0.9243. Min Act: -0.1700
Data Index: 6522835 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0718. Min Range: -1.0718
Max Act: 0.9072. Min Act: -0.1700
Data Index: 1122074 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0718. Min Range: -1.0718
Max Act: 0.8986. Min Act: -0.1700
Data Index: 4767766 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0718. Min Range: -1.0718
Max Act: 0.8986. Min Act: -0.1700
Data Index: 6837950 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0718. Min Range: -1.0718
Max Act: 0.8901. Min Act: -0.1700
Data Index: 612295 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0718. Min Range: -1.0718
Max Act: 0.9072. Min Act: -0.1700
Data Index: 962185 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0718. Min Range: -1.0718
Max Act: 0.8816. Min Act: -0.1700
Data Index: 7116494 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0718. Min Range: -1.0718
Max Act: 0.9072. Min Act: -0.1700
Data Index: 2023769 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0718. Min Range: -1.0718
Max Act: 0.8901. Min Act: -0.1700
Data Index: 1794318 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0718. Min Range: -1.0718
Max Act: 0.8986. Min Act: -0.1700
Data Index: 1777452 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0718. Min Range: -1.0718
Max Act: 0.8816. Min Act: -0.1700
Data Index: 8632832 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0718. Min Range: -1.0718
Max Act: 0.8816. Min Act: -0.1696
Data Index: 1100768 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19