Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 871 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3455. Min Range: -3.3455
Max Act: 3.3455. Min Act: -0.1700
Data Index: 4716853 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3455. Min Range: -3.3455
Max Act: 3.2042. Min Act: -0.1700
Data Index: 3371261 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3455. Min Range: -3.3455
Max Act: 3.2356. Min Act: -0.1700
Data Index: 5972443 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3455. Min Range: -3.3455
Max Act: 3.2356. Min Act: -0.1700
Data Index: 5550214 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3455. Min Range: -3.3455
Max Act: 3.1884. Min Act: -0.1700
Data Index: 8008047 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3455. Min Range: -3.3455
Max Act: 3.1727. Min Act: -0.1700
Data Index: 1441862 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3455. Min Range: -3.3455
Max Act: 3.1727. Min Act: -0.1700
Data Index: 400258 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3455. Min Range: -3.3455
Max Act: 3.1727. Min Act: -0.1700
Data Index: 1141745 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3455. Min Range: -3.3455
Max Act: 3.1727. Min Act: -0.1700
Data Index: 3819261 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3455. Min Range: -3.3455
Max Act: 3.1727. Min Act: -0.1700
Data Index: 3319382 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3455. Min Range: -3.3455
Max Act: 3.1255. Min Act: -0.1700
Data Index: 2824121 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3455. Min Range: -3.3455
Max Act: 3.1097. Min Act: -0.1700
Data Index: 4711565 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3455. Min Range: -3.3455
Max Act: 3.0782. Min Act: -0.1700
Data Index: 2247268 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3455. Min Range: -3.3455
Max Act: 3.0940. Min Act: -0.1700
Data Index: 8006602 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3455. Min Range: -3.3455
Max Act: 3.0940. Min Act: -0.1700
Data Index: 104566 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3455. Min Range: -3.3455
Max Act: 3.0940. Min Act: -0.1700
Data Index: 3474949 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3455. Min Range: -3.3455
Max Act: 3.0782. Min Act: -0.1700
Data Index: 982062 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3455. Min Range: -3.3455
Max Act: 3.0782. Min Act: -0.1700
Data Index: 4937795 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3455. Min Range: -3.3455
Max Act: 3.0782. Min Act: -0.1700
Data Index: 6651098 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3455. Min Range: -3.3455
Max Act: 3.0782. Min Act: -0.1700
Data Index: 1631787 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19