Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 28 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0946. Min Range: -5.0946
Max Act: 5.0946. Min Act: -0.1700
Data Index: 5537384 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0946. Min Range: -5.0946
Max Act: 5.0633. Min Act: -0.1700
Data Index: 2575813 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0946. Min Range: -5.0946
Max Act: 4.9383. Min Act: -0.1700
Data Index: 3386680 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0946. Min Range: -5.0946
Max Act: 4.8133. Min Act: -0.1700
Data Index: 6908069 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0946. Min Range: -5.0946
Max Act: 4.8133. Min Act: -0.1700
Data Index: 1847007 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0946. Min Range: -5.0946
Max Act: 4.8133. Min Act: -0.1700
Data Index: 3898804 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0946. Min Range: -5.0946
Max Act: 4.8133. Min Act: -0.1700
Data Index: 6528702 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0946. Min Range: -5.0946
Max Act: 4.8446. Min Act: -0.1700
Data Index: 4867281 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0946. Min Range: -5.0946
Max Act: 4.7508. Min Act: -0.1700
Data Index: 4010157 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0946. Min Range: -5.0946
Max Act: 4.7821. Min Act: -0.1700
Data Index: 3898805 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0946. Min Range: -5.0946
Max Act: 4.7508. Min Act: -0.1700
Data Index: 7685063 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0946. Min Range: -5.0946
Max Act: 4.7508. Min Act: -0.1700
Data Index: 4624755 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0946. Min Range: -5.0946
Max Act: 4.7196. Min Act: -0.1700
Data Index: 1251243 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0946. Min Range: -5.0946
Max Act: 4.7196. Min Act: -0.1700
Data Index: 7164184 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0946. Min Range: -5.0946
Max Act: 4.6571. Min Act: -0.1700
Data Index: 8452775 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0946. Min Range: -5.0946
Max Act: 4.6883. Min Act: -0.1700
Data Index: 1433457 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0946. Min Range: -5.0946
Max Act: 4.6883. Min Act: -0.1700
Data Index: 3397822 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0946. Min Range: -5.0946
Max Act: 4.6883. Min Act: -0.1700
Data Index: 1251237 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0946. Min Range: -5.0946
Max Act: 4.6571. Min Act: -0.1700
Data Index: 6285368 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0946. Min Range: -5.0946
Max Act: 4.6571. Min Act: -0.1700
Data Index: 5484096 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #19