Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2831 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5083. Min Range: -5.5083
Max Act: 5.5083. Min Act: -0.1700
Data Index: 6244688 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5083. Min Range: -5.5083
Max Act: 5.5083. Min Act: -0.1700
Data Index: 182633 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5083. Min Range: -5.5083
Max Act: 5.4770. Min Act: -0.1700
Data Index: 7844627 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5083. Min Range: -5.5083
Max Act: 5.4458. Min Act: -0.1700
Data Index: 4674564 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5083. Min Range: -5.5083
Max Act: 5.4458. Min Act: -0.1700
Data Index: 5549947 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5083. Min Range: -5.5083
Max Act: 5.4458. Min Act: -0.1700
Data Index: 410704 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5083. Min Range: -5.5083
Max Act: 5.4145. Min Act: -0.1700
Data Index: 2459782 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5083. Min Range: -5.5083
Max Act: 5.4145. Min Act: -0.1700
Data Index: 5860722 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5083. Min Range: -5.5083
Max Act: 5.4145. Min Act: -0.1700
Data Index: 2702969 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5083. Min Range: -5.5083
Max Act: 5.4145. Min Act: -0.1700
Data Index: 4138613 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5083. Min Range: -5.5083
Max Act: 5.3833. Min Act: -0.1700
Data Index: 866073 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5083. Min Range: -5.5083
Max Act: 5.4145. Min Act: -0.1700
Data Index: 3930686 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5083. Min Range: -5.5083
Max Act: 5.3833. Min Act: -0.1700
Data Index: 3638767 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5083. Min Range: -5.5083
Max Act: 5.4145. Min Act: -0.1700
Data Index: 7953600 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5083. Min Range: -5.5083
Max Act: 5.3833. Min Act: -0.1700
Data Index: 1870476 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5083. Min Range: -5.5083
Max Act: 5.3833. Min Act: -0.1700
Data Index: 2131494 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5083. Min Range: -5.5083
Max Act: 5.3520. Min Act: -0.1700
Data Index: 817629 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5083. Min Range: -5.5083
Max Act: 5.3520. Min Act: -0.1700
Data Index: 2230929 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5083. Min Range: -5.5083
Max Act: 5.3520. Min Act: -0.1700
Data Index: 5320278 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5083. Min Range: -5.5083
Max Act: 5.3833. Min Act: -0.1700
Data Index: 1736787 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19