Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2571 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2774. Min Range: -5.2774
Max Act: 5.2774. Min Act: -0.1700
Data Index: 5283629 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2774. Min Range: -5.2774
Max Act: 5.2774. Min Act: -0.1699
Data Index: 2436801 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2774. Min Range: -5.2774
Max Act: 5.2461. Min Act: -0.1700
Data Index: 6622071 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2774. Min Range: -5.2774
Max Act: 5.1836. Min Act: -0.1699
Data Index: 5586140 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2774. Min Range: -5.2774
Max Act: 5.1836. Min Act: -0.1700
Data Index: 6200407 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2774. Min Range: -5.2774
Max Act: 5.1836. Min Act: -0.1700
Data Index: 6690145 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2774. Min Range: -5.2774
Max Act: 5.1836. Min Act: -0.1700
Data Index: 66067 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2774. Min Range: -5.2774
Max Act: 5.1836. Min Act: -0.1700
Data Index: 6941471 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2774. Min Range: -5.2774
Max Act: 5.1524. Min Act: -0.1698
Data Index: 745073 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2774. Min Range: -5.2774
Max Act: 5.1836. Min Act: -0.1700
Data Index: 8411914 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2774. Min Range: -5.2774
Max Act: 5.1524. Min Act: -0.1700
Data Index: 1298262 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2774. Min Range: -5.2774
Max Act: 5.1836. Min Act: -0.1700
Data Index: 3209245 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2774. Min Range: -5.2774
Max Act: 5.1524. Min Act: -0.1700
Data Index: 4027919 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2774. Min Range: -5.2774
Max Act: 5.1524. Min Act: -0.1700
Data Index: 8708507 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2774. Min Range: -5.2774
Max Act: 5.1524. Min Act: -0.1700
Data Index: 4591880 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2774. Min Range: -5.2774
Max Act: 5.1524. Min Act: -0.1700
Data Index: 181692 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2774. Min Range: -5.2774
Max Act: 5.1524. Min Act: -0.1699
Data Index: 388709 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2774. Min Range: -5.2774
Max Act: 5.1211. Min Act: -0.1699
Data Index: 1491916 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2774. Min Range: -5.2774
Max Act: 5.1211. Min Act: -0.1700
Data Index: 4694328 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2774. Min Range: -5.2774
Max Act: 5.1211. Min Act: -0.1700
Data Index: 3771215 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19