Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3749 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8057. Min Range: -4.8057
Max Act: 4.7745. Min Act: -0.1700
Data Index: 3802098 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8057. Min Range: -4.8057
Max Act: 4.8057. Min Act: -0.1700
Data Index: 6077834 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8057. Min Range: -4.8057
Max Act: 4.8057. Min Act: -0.1700
Data Index: 8011174 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8057. Min Range: -4.8057
Max Act: 4.7745. Min Act: -0.1700
Data Index: 8479906 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8057. Min Range: -4.8057
Max Act: 4.7432. Min Act: -0.1700
Data Index: 7429647 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8057. Min Range: -4.8057
Max Act: 4.7745. Min Act: -0.1700
Data Index: 602638 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8057. Min Range: -4.8057
Max Act: 4.7432. Min Act: -0.1700
Data Index: 5750635 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8057. Min Range: -4.8057
Max Act: 4.7432. Min Act: -0.1700
Data Index: 2126007 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8057. Min Range: -4.8057
Max Act: 4.7120. Min Act: -0.1700
Data Index: 349407 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8057. Min Range: -4.8057
Max Act: 4.7120. Min Act: -0.1700
Data Index: 2389963 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8057. Min Range: -4.8057
Max Act: 4.7120. Min Act: -0.1700
Data Index: 7370520 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8057. Min Range: -4.8057
Max Act: 4.7120. Min Act: -0.1700
Data Index: 5409366 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8057. Min Range: -4.8057
Max Act: 4.6807. Min Act: -0.1700
Data Index: 2389971 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8057. Min Range: -4.8057
Max Act: 4.6807. Min Act: -0.1700
Data Index: 3403556 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8057. Min Range: -4.8057
Max Act: 4.7120. Min Act: -0.1700
Data Index: 8654783 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8057. Min Range: -4.8057
Max Act: 4.7120. Min Act: -0.1700
Data Index: 1527152 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8057. Min Range: -4.8057
Max Act: 4.6495. Min Act: -0.1700
Data Index: 3412713 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8057. Min Range: -4.8057
Max Act: 4.6182. Min Act: -0.1700
Data Index: 1116075 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8057. Min Range: -4.8057
Max Act: 4.6182. Min Act: -0.1700
Data Index: 3721795 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8057. Min Range: -4.8057
Max Act: 4.6495. Min Act: -0.1700
Data Index: 2389961 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19