Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 625 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0312. Min Range: -6.0312
Max Act: 6.0312. Min Act: -0.1700
Data Index: 6509019 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0312. Min Range: -6.0312
Max Act: 5.9999. Min Act: -0.1700
Data Index: 4218458 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0312. Min Range: -6.0312
Max Act: 5.9374. Min Act: -0.1700
Data Index: 3907300 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0312. Min Range: -6.0312
Max Act: 5.9062. Min Act: -0.1700
Data Index: 1516151 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0312. Min Range: -6.0312
Max Act: 5.8437. Min Act: -0.1700
Data Index: 823532 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0312. Min Range: -6.0312
Max Act: 5.8749. Min Act: -0.1700
Data Index: 1527835 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0312. Min Range: -6.0312
Max Act: 5.8749. Min Act: -0.1700
Data Index: 1004884 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0312. Min Range: -6.0312
Max Act: 5.8437. Min Act: -0.1700
Data Index: 8202752 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0312. Min Range: -6.0312
Max Act: 5.8437. Min Act: -0.1700
Data Index: 6653905 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0312. Min Range: -6.0312
Max Act: 5.8437. Min Act: -0.1700
Data Index: 3148542 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0312. Min Range: -6.0312
Max Act: 5.8124. Min Act: -0.1700
Data Index: 3907301 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0312. Min Range: -6.0312
Max Act: 5.8124. Min Act: -0.1700
Data Index: 7589674 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0312. Min Range: -6.0312
Max Act: 5.8124. Min Act: -0.1700
Data Index: 8552924 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0312. Min Range: -6.0312
Max Act: 5.8124. Min Act: -0.1700
Data Index: 4444207 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0312. Min Range: -6.0312
Max Act: 5.7812. Min Act: -0.1700
Data Index: 5473982 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0312. Min Range: -6.0312
Max Act: 5.7812. Min Act: -0.1700
Data Index: 618665 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0312. Min Range: -6.0312
Max Act: 5.7812. Min Act: -0.1700
Data Index: 4082771 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0312. Min Range: -6.0312
Max Act: 5.7812. Min Act: -0.1700
Data Index: 2493928 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0312. Min Range: -6.0312
Max Act: 5.7499. Min Act: -0.1700
Data Index: 6008779 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0312. Min Range: -6.0312
Max Act: 5.7187. Min Act: -0.1700
Data Index: 5595233 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #19