Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1953 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8610. Min Range: -6.8610
Max Act: 6.8610. Min Act: -0.1700
Data Index: 6986512 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8610. Min Range: -6.8610
Max Act: 6.8610. Min Act: -0.1700
Data Index: 5176821 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8610. Min Range: -6.8610
Max Act: 6.7985. Min Act: -0.1700
Data Index: 4044654 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8610. Min Range: -6.8610
Max Act: 6.7985. Min Act: -0.1700
Data Index: 3569902 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8610. Min Range: -6.8610
Max Act: 6.7673. Min Act: -0.1700
Data Index: 8457529 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8610. Min Range: -6.8610
Max Act: 6.7048. Min Act: -0.1700
Data Index: 5191314 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8610. Min Range: -6.8610
Max Act: 6.7048. Min Act: -0.1700
Data Index: 1568526 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8610. Min Range: -6.8610
Max Act: 6.6735. Min Act: -0.1700
Data Index: 3568649 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8610. Min Range: -6.8610
Max Act: 6.7048. Min Act: -0.1700
Data Index: 4958491 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8610. Min Range: -6.8610
Max Act: 6.6735. Min Act: -0.1700
Data Index: 6442145 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8610. Min Range: -6.8610
Max Act: 6.6423. Min Act: -0.1700
Data Index: 703443 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8610. Min Range: -6.8610
Max Act: 6.6423. Min Act: -0.1700
Data Index: 486877 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8610. Min Range: -6.8610
Max Act: 6.6423. Min Act: -0.1700
Data Index: 872634 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8610. Min Range: -6.8610
Max Act: 6.6110. Min Act: -0.1700
Data Index: 6142918 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8610. Min Range: -6.8610
Max Act: 6.5798. Min Act: -0.1700
Data Index: 8278899 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8610. Min Range: -6.8610
Max Act: 6.5798. Min Act: -0.1700
Data Index: 930167 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8610. Min Range: -6.8610
Max Act: 6.5798. Min Act: -0.1700
Data Index: 755130 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8610. Min Range: -6.8610
Max Act: 6.5485. Min Act: -0.1700
Data Index: 4514025 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8610. Min Range: -6.8610
Max Act: 6.5485. Min Act: -0.1700
Data Index: 1858972 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8610. Min Range: -6.8610
Max Act: 6.5485. Min Act: -0.1700
Data Index: 3938775 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19