Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2628 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2072. Min Range: -4.2072
Max Act: 4.2072. Min Act: -0.1700
Data Index: 189435 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2072. Min Range: -4.2072
Max Act: 4.0196. Min Act: -0.1700
Data Index: 1472207 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2072. Min Range: -4.2072
Max Act: 4.0509. Min Act: -0.1700
Data Index: 3095401 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2072. Min Range: -4.2072
Max Act: 3.9884. Min Act: -0.1700
Data Index: 7592943 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2072. Min Range: -4.2072
Max Act: 4.0196. Min Act: -0.1700
Data Index: 1295172 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2072. Min Range: -4.2072
Max Act: 4.0196. Min Act: -0.1700
Data Index: 2187789 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2072. Min Range: -4.2072
Max Act: 3.9884. Min Act: -0.1700
Data Index: 315283 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2072. Min Range: -4.2072
Max Act: 3.9884. Min Act: -0.1700
Data Index: 7414407 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2072. Min Range: -4.2072
Max Act: 3.9884. Min Act: -0.1700
Data Index: 8308507 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2072. Min Range: -4.2072
Max Act: 3.9571. Min Act: -0.1700
Data Index: 1453362 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2072. Min Range: -4.2072
Max Act: 3.9415. Min Act: -0.1700
Data Index: 8632350 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2072. Min Range: -4.2072
Max Act: 3.9571. Min Act: -0.1700
Data Index: 8013370 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2072. Min Range: -4.2072
Max Act: 3.9415. Min Act: -0.1700
Data Index: 1240514 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2072. Min Range: -4.2072
Max Act: 3.9571. Min Act: -0.1700
Data Index: 7995707 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2072. Min Range: -4.2072
Max Act: 3.9415. Min Act: -0.1700
Data Index: 1674117 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2072. Min Range: -4.2072
Max Act: 3.9415. Min Act: -0.1700
Data Index: 6357630 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2072. Min Range: -4.2072
Max Act: 3.8946. Min Act: -0.1700
Data Index: 4075786 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2072. Min Range: -4.2072
Max Act: 3.9415. Min Act: -0.1700
Data Index: 4686523 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2072. Min Range: -4.2072
Max Act: 3.9102. Min Act: -0.1700
Data Index: 3340988 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2072. Min Range: -4.2072
Max Act: 3.8789. Min Act: -0.1700
Data Index: 5251016 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #19