Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1941 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7999. Min Range: -3.7999
Max Act: 3.7686. Min Act: -0.1700
Data Index: 1425096 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7999. Min Range: -3.7999
Max Act: 3.7999. Min Act: -0.1700
Data Index: 4293297 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7999. Min Range: -3.7999
Max Act: 3.7999. Min Act: -0.1700
Data Index: 1697067 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7999. Min Range: -3.7999
Max Act: 3.7686. Min Act: -0.1700
Data Index: 4732770 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7999. Min Range: -3.7999
Max Act: 3.7686. Min Act: -0.1700
Data Index: 8387911 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7999. Min Range: -3.7999
Max Act: 3.7373. Min Act: -0.1700
Data Index: 8193093 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7999. Min Range: -3.7999
Max Act: 3.7686. Min Act: -0.1700
Data Index: 4135363 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7999. Min Range: -3.7999
Max Act: 3.7373. Min Act: -0.1700
Data Index: 3310881 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7999. Min Range: -3.7999
Max Act: 3.7060. Min Act: -0.1700
Data Index: 8344767 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7999. Min Range: -3.7999
Max Act: 3.7060. Min Act: -0.1700
Data Index: 6718542 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7999. Min Range: -3.7999
Max Act: 3.7060. Min Act: -0.1700
Data Index: 2243201 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7999. Min Range: -3.7999
Max Act: 3.6747. Min Act: -0.1700
Data Index: 1617996 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7999. Min Range: -3.7999
Max Act: 3.6747. Min Act: -0.1700
Data Index: 3317966 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7999. Min Range: -3.7999
Max Act: 3.6747. Min Act: -0.1700
Data Index: 4321998 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7999. Min Range: -3.7999
Max Act: 3.6435. Min Act: -0.1700
Data Index: 2067027 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7999. Min Range: -3.7999
Max Act: 3.6435. Min Act: -0.1700
Data Index: 4980450 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7999. Min Range: -3.7999
Max Act: 3.6435. Min Act: -0.1700
Data Index: 5391380 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7999. Min Range: -3.7999
Max Act: 3.6435. Min Act: -0.1700
Data Index: 5701933 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7999. Min Range: -3.7999
Max Act: 3.6435. Min Act: -0.1700
Data Index: 5805667 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7999. Min Range: -3.7999
Max Act: 3.6435. Min Act: -0.1700
Data Index: 6170097 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19