Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4035 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9557. Min Range: -4.9557
Max Act: 4.9557. Min Act: -0.1700
Data Index: 4983848 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9557. Min Range: -4.9557
Max Act: 4.9245. Min Act: -0.1700
Data Index: 5899992 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9557. Min Range: -4.9557
Max Act: 4.8620. Min Act: -0.1700
Data Index: 6193349 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9557. Min Range: -4.9557
Max Act: 4.7995. Min Act: -0.1700
Data Index: 4030817 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9557. Min Range: -4.9557
Max Act: 4.7995. Min Act: -0.1700
Data Index: 4248054 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9557. Min Range: -4.9557
Max Act: 4.7995. Min Act: -0.1700
Data Index: 6480243 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9557. Min Range: -4.9557
Max Act: 4.7995. Min Act: -0.1700
Data Index: 3084804 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9557. Min Range: -4.9557
Max Act: 4.7995. Min Act: -0.1700
Data Index: 2091515 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9557. Min Range: -4.9557
Max Act: 4.7682. Min Act: -0.1700
Data Index: 3580363 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9557. Min Range: -4.9557
Max Act: 4.7682. Min Act: -0.1700
Data Index: 6415490 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9557. Min Range: -4.9557
Max Act: 4.7682. Min Act: -0.1700
Data Index: 3003446 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9557. Min Range: -4.9557
Max Act: 4.7682. Min Act: -0.1700
Data Index: 1260740 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9557. Min Range: -4.9557
Max Act: 4.7057. Min Act: -0.1700
Data Index: 759372 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9557. Min Range: -4.9557
Max Act: 4.7057. Min Act: -0.1700
Data Index: 5313929 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9557. Min Range: -4.9557
Max Act: 4.7370. Min Act: -0.1700
Data Index: 3308696 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9557. Min Range: -4.9557
Max Act: 4.6745. Min Act: -0.1700
Data Index: 292245 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9557. Min Range: -4.9557
Max Act: 4.7057. Min Act: -0.1700
Data Index: 406455 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9557. Min Range: -4.9557
Max Act: 4.6745. Min Act: -0.1700
Data Index: 2058532 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9557. Min Range: -4.9557
Max Act: 4.6745. Min Act: -0.1700
Data Index: 4594209 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9557. Min Range: -4.9557
Max Act: 4.6745. Min Act: -0.1700
Data Index: 1213849 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #19