Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3474 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1685. Min Range: -3.1685
Max Act: 3.1685. Min Act: -0.1700
Data Index: 8262590 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1685. Min Range: -3.1685
Max Act: 3.1370. Min Act: -0.1700
Data Index: 4085444 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1685. Min Range: -3.1685
Max Act: 3.0740. Min Act: -0.1700
Data Index: 6337181 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1685. Min Range: -3.1685
Max Act: 3.0582. Min Act: -0.1700
Data Index: 8374963 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1685. Min Range: -3.1685
Max Act: 3.0582. Min Act: -0.1700
Data Index: 1852282 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1685. Min Range: -3.1685
Max Act: 3.0424. Min Act: -0.1700
Data Index: 1641739 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1685. Min Range: -3.1685
Max Act: 3.0266. Min Act: -0.1700
Data Index: 7258354 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1685. Min Range: -3.1685
Max Act: 3.0424. Min Act: -0.1700
Data Index: 3927721 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1685. Min Range: -3.1685
Max Act: 3.0266. Min Act: -0.1700
Data Index: 542168 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1685. Min Range: -3.1685
Max Act: 3.0266. Min Act: -0.1700
Data Index: 4527622 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1685. Min Range: -3.1685
Max Act: 3.0266. Min Act: -0.1700
Data Index: 1874840 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1685. Min Range: -3.1685
Max Act: 3.0109. Min Act: -0.1700
Data Index: 5709123 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1685. Min Range: -3.1685
Max Act: 2.9951. Min Act: -0.1700
Data Index: 178861 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1685. Min Range: -3.1685
Max Act: 2.9951. Min Act: -0.1700
Data Index: 7367566 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1685. Min Range: -3.1685
Max Act: 2.9951. Min Act: -0.1700
Data Index: 7717188 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1685. Min Range: -3.1685
Max Act: 2.9951. Min Act: -0.1700
Data Index: 1835435 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1685. Min Range: -3.1685
Max Act: 2.9951. Min Act: -0.1700
Data Index: 3799956 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1685. Min Range: -3.1685
Max Act: 2.9951. Min Act: -0.1700
Data Index: 1827185 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1685. Min Range: -3.1685
Max Act: 2.9792. Min Act: -0.1700
Data Index: 3761826 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1685. Min Range: -3.1685
Max Act: 2.9951. Min Act: -0.1700
Data Index: 5752310 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19