Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5065 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.1878. Min Range: -1.1878
Max Act: 1.1878. Min Act: -0.1700
Data Index: 5765971 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1878. Min Range: -1.1878
Max Act: 1.1527. Min Act: -0.1700
Data Index: 7865665 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1878. Min Range: -1.1878
Max Act: 1.1263. Min Act: -0.1700
Data Index: 4075630 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1878. Min Range: -1.1878
Max Act: 1.1000. Min Act: -0.1700
Data Index: 7218992 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1878. Min Range: -1.1878
Max Act: 1.0913. Min Act: -0.1700
Data Index: 5364583 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1878. Min Range: -1.1878
Max Act: 1.0913. Min Act: -0.1700
Data Index: 7219002 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1878. Min Range: -1.1878
Max Act: 1.0825. Min Act: -0.1700
Data Index: 7219005 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1878. Min Range: -1.1878
Max Act: 1.0825. Min Act: -0.1700
Data Index: 7373731 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1878. Min Range: -1.1878
Max Act: 1.0738. Min Act: -0.1700
Data Index: 7218996 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1878. Min Range: -1.1878
Max Act: 1.0825. Min Act: -0.1700
Data Index: 4306231 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1878. Min Range: -1.1878
Max Act: 1.0738. Min Act: -0.1700
Data Index: 8805198 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1878. Min Range: -1.1878
Max Act: 1.0738. Min Act: -0.1700
Data Index: 7219001 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1878. Min Range: -1.1878
Max Act: 1.0738. Min Act: -0.1700
Data Index: 7219006 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1878. Min Range: -1.1878
Max Act: 1.0738. Min Act: -0.1700
Data Index: 7218983 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1878. Min Range: -1.1878
Max Act: 1.0738. Min Act: -0.1700
Data Index: 1276901 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1878. Min Range: -1.1878
Max Act: 1.0825. Min Act: -0.1700
Data Index: 1276899 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1878. Min Range: -1.1878
Max Act: 1.0650. Min Act: -0.1700
Data Index: 7219000 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1878. Min Range: -1.1878
Max Act: 1.0650. Min Act: -0.1700
Data Index: 7218995 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1878. Min Range: -1.1878
Max Act: 1.0650. Min Act: -0.1700
Data Index: 7218994 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1878. Min Range: -1.1878
Max Act: 1.0650. Min Act: -0.1700
Data Index: 694575 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19