Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2131 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5541. Min Range: -1.5541
Max Act: 1.5541. Min Act: -0.1700
Data Index: 5128015 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5541. Min Range: -1.5541
Max Act: 1.5190. Min Act: -0.1700
Data Index: 5128013 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5541. Min Range: -1.5541
Max Act: 1.5190. Min Act: -0.1700
Data Index: 4877124 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5541. Min Range: -1.5541
Max Act: 1.5015. Min Act: -0.1700
Data Index: 5537158 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5541. Min Range: -1.5541
Max Act: 1.5015. Min Act: -0.1700
Data Index: 6048311 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5541. Min Range: -1.5541
Max Act: 1.5015. Min Act: -0.1700
Data Index: 5537167 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5541. Min Range: -1.5541
Max Act: 1.5015. Min Act: -0.1700
Data Index: 7955743 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5541. Min Range: -1.5541
Max Act: 1.5015. Min Act: -0.1700
Data Index: 5012572 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5541. Min Range: -1.5541
Max Act: 1.5015. Min Act: -0.1700
Data Index: 5537154 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5541. Min Range: -1.5541
Max Act: 1.5015. Min Act: -0.1700
Data Index: 7367373 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5541. Min Range: -1.5541
Max Act: 1.5015. Min Act: -0.1700
Data Index: 6670952 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5541. Min Range: -1.5541
Max Act: 1.4839. Min Act: -0.1700
Data Index: 4892270 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5541. Min Range: -1.5541
Max Act: 1.4839. Min Act: -0.1700
Data Index: 5537156 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5541. Min Range: -1.5541
Max Act: 1.5015. Min Act: -0.1700
Data Index: 5486257 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5541. Min Range: -1.5541
Max Act: 1.4839. Min Act: -0.1700
Data Index: 5537170 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5541. Min Range: -1.5541
Max Act: 1.5015. Min Act: -0.1700
Data Index: 5537152 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5541. Min Range: -1.5541
Max Act: 1.5015. Min Act: -0.1700
Data Index: 1407259 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5541. Min Range: -1.5541
Max Act: 1.5015. Min Act: -0.1700
Data Index: 5537160 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5541. Min Range: -1.5541
Max Act: 1.5015. Min Act: -0.1700
Data Index: 3565641 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5541. Min Range: -1.5541
Max Act: 1.4839. Min Act: -0.1700
Data Index: 5708923 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19