Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3685 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1847. Min Range: -6.1847
Max Act: 6.1847. Min Act: -0.1700
Data Index: 740374 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1847. Min Range: -6.1847
Max Act: 5.9972. Min Act: -0.1700
Data Index: 673612 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1847. Min Range: -6.1847
Max Act: 5.9347. Min Act: -0.1700
Data Index: 7977043 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1847. Min Range: -6.1847
Max Act: 5.8722. Min Act: -0.1700
Data Index: 1826616 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1847. Min Range: -6.1847
Max Act: 5.8097. Min Act: -0.1700
Data Index: 6490994 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1847. Min Range: -6.1847
Max Act: 5.7785. Min Act: -0.1700
Data Index: 2466128 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1847. Min Range: -6.1847
Max Act: 5.7160. Min Act: -0.1700
Data Index: 6547174 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1847. Min Range: -6.1847
Max Act: 5.6535. Min Act: -0.1700
Data Index: 5827544 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1847. Min Range: -6.1847
Max Act: 5.6535. Min Act: -0.1700
Data Index: 7110100 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1847. Min Range: -6.1847
Max Act: 5.6222. Min Act: -0.1700
Data Index: 8116134 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1847. Min Range: -6.1847
Max Act: 5.6535. Min Act: -0.1700
Data Index: 184854 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1847. Min Range: -6.1847
Max Act: 5.6535. Min Act: -0.1700
Data Index: 6184995 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1847. Min Range: -6.1847
Max Act: 5.6222. Min Act: -0.1700
Data Index: 255863 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1847. Min Range: -6.1847
Max Act: 5.6222. Min Act: -0.1700
Data Index: 5417944 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1847. Min Range: -6.1847
Max Act: 5.6222. Min Act: -0.1700
Data Index: 656458 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1847. Min Range: -6.1847
Max Act: 5.5910. Min Act: -0.1700
Data Index: 4141770 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1847. Min Range: -6.1847
Max Act: 5.6222. Min Act: -0.1700
Data Index: 6976525 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1847. Min Range: -6.1847
Max Act: 5.5910. Min Act: -0.1700
Data Index: 2947683 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1847. Min Range: -6.1847
Max Act: 5.5910. Min Act: -0.1700
Data Index: 982516 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1847. Min Range: -6.1847
Max Act: 5.5597. Min Act: -0.1700
Data Index: 3113727 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19