Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 672 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3069. Min Range: -3.3069
Max Act: 3.3069. Min Act: -0.1700
Data Index: 8024596 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3069. Min Range: -3.3069
Max Act: 3.2441. Min Act: -0.1700
Data Index: 2383539 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3069. Min Range: -3.3069
Max Act: 3.2284. Min Act: -0.1700
Data Index: 338122 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3069. Min Range: -3.3069
Max Act: 3.2284. Min Act: -0.1700
Data Index: 3056672 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3069. Min Range: -3.3069
Max Act: 3.2284. Min Act: -0.1700
Data Index: 2878808 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3069. Min Range: -3.3069
Max Act: 3.2126. Min Act: -0.1700
Data Index: 3413964 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3069. Min Range: -3.3069
Max Act: 3.2126. Min Act: -0.1700
Data Index: 328860 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3069. Min Range: -3.3069
Max Act: 3.2126. Min Act: -0.1700
Data Index: 5825598 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3069. Min Range: -3.3069
Max Act: 3.2126. Min Act: -0.1700
Data Index: 4206605 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3069. Min Range: -3.3069
Max Act: 3.1969. Min Act: -0.1700
Data Index: 6733499 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3069. Min Range: -3.3069
Max Act: 3.1969. Min Act: -0.1700
Data Index: 7406967 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3069. Min Range: -3.3069
Max Act: 3.1969. Min Act: -0.1700
Data Index: 7769745 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3069. Min Range: -3.3069
Max Act: 3.1969. Min Act: -0.1700
Data Index: 925557 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3069. Min Range: -3.3069
Max Act: 3.1969. Min Act: -0.1700
Data Index: 2936808 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3069. Min Range: -3.3069
Max Act: 3.1812. Min Act: -0.1700
Data Index: 965313 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3069. Min Range: -3.3069
Max Act: 3.1655. Min Act: -0.1700
Data Index: 745082 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3069. Min Range: -3.3069
Max Act: 3.1812. Min Act: -0.1700
Data Index: 7431108 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3069. Min Range: -3.3069
Max Act: 3.1812. Min Act: -0.1700
Data Index: 3650627 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3069. Min Range: -3.3069
Max Act: 3.1812. Min Act: -0.1700
Data Index: 6875828 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3069. Min Range: -3.3069
Max Act: 3.1812. Min Act: -0.1700
Data Index: 6827647 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19